Awesome
Awesome Incremental Learning / Lifelong learning
Survey
- <a name="todo"></a> Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy (JBCS 2024) [paper]
- <a name="todo"></a> Class-Incremental Learning: A Survey (TPAMI 2024) [paper][code]
- <a name="todo"></a> Continual Learning with Pre-Trained Models: A Survey (IJCAI 2024) [paper][code]
- <a name="todo"></a> Continual Learning of Large Language Models: A Comprehensive Survey (arXiv 2024) [paper][code]
- <a name="todo"></a> A Comprehensive Survey of Continual Learning: Theory, Method and Application (TPAMI 2024) [paper]
- <a name="todo"></a> A Comprehensive Empirical Evaluation on Online Continual Learning (ICCV Workshop 2023) [paper][code]
- <a name="todo"></a> A Survey on Few-Shot Class-Incremental Learning (Neural Networks 2024) [paper]
- <a name="todo"></a> A wholistic view of continual learning with deep neural networks: Forgotten lessons and the bridge to active and open world learning (Neural Networks 2023) [paper]
- <a name="todo"></a>An Introduction to Lifelong Supervised Learning (arXiv 2022) [paper]
- <a name="todo"></a> A Survey on Incremental Update for Neural Recommender Systems (arXiv 2023) [paper]
- <a name="todo"></a> Continual Learning of Natural Language Processing Tasks: A Survey (arXiv 2022) [paper]
- <a name="todo"></a> Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworks (arXiv 2022) [paper]
- <a name="todo"></a> Recent Advances of Continual Learning in Computer Vision: An Overview (arXiv 2021) [paper]
- <a name="todo"></a> Replay in Deep Learning: Current Approaches and Missing Biological Elements (Neural Computation 2021) [paper]
- <a name="todo"></a> Online Continual Learning in Image Classification: An Empirical Survey (Neurocomputing 2021) [paper] [code]
- <a name="todo"></a> Continual Lifelong Learning in Natural Language Processing: A Survey (COLING 2020) [paper]
- <a name="todo"></a> Class-incremental learning: survey and performance evaluation (TPAMI 2022) [paper] [code]
- <a name="todo"></a> A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks (Neural Networks) [paper] [code]
- <a name="todo"></a> A continual learning survey: Defying forgetting in classification tasks (TPAMI 2021) [paper] [arxiv]
- <a name="todo"></a> Continual Lifelong Learning with Neural Networks: A Review (Neural Networks) [paper]
- <a name="todo"></a> Three scenarios for continual learning (Nature Machine Intelligence 2022) [paper][code]
Papers
2024
-
<a name="todo"></a> Online Continuous Generalized Category Discovery (ECCV24)[paper][code]
-
<a name="todo"></a> Class-incremental Learning for Time Series: Benchmark and Evaluation (KDD24)[paper][code]
-
<a name="todo"></a> Harnessing Neural Unit Dynamics for Effective and Scalable Class-Incremental Learning (ICML24)[paper]
-
<a name="todo"></a> Multi-layer Rehearsal Feature Augmentation for Class-Incremental Learning (ICML24)[paper][code]
-
<a name="todo"></a> Regularizing with Pseudo-Negatives for Continual Self-Supervised Learning (ICML24)[paper]
-
<a name="todo"></a> Learning to Continually Learn with the Bayesian Principle (ICML24)[paper][code]
-
<a name="todo"></a> Rethinking Momentum Knowledge Distillation in Online Continual Learning (ICML24)[paper][code]
-
<a name="todo"></a> Layerwise Proximal Replay: A Proximal Point Method for Online Continual Learning (ICML24)[paper]
-
<a name="todo"></a> Bayesian Adaptation of Network Depth and Width for Continual Learning (ICML24)[paper]
-
<a name="todo"></a> STELLA: Continual Audio-Video Pre-training with SpatioTemporal Localized Alignment (ICML24)[paper][code]
-
<a name="todo"></a> On the Diminishing Returns of Width for Continual Learning (ICML24)[paper][code]
-
<a name="todo"></a> Compositional Few-Shot Class-Incremental Learning (ICML24)[paper][code]
-
<a name="todo"></a> Rapid Learning without Catastrophic Forgetting in the Morris Water Maze (ICML24)[paper][code]
-
<a name="todo"></a> Understanding Forgetting in Continual Learning with Linear Regression (ICML24)[paper]
-
<a name="todo"></a> Mitigating Catastrophic Forgetting in Online Continual Learning by Modeling Previous Task Interrelations via Pareto Optimization (ICML24)[paper]
-
<a name="todo"></a> Task-aware Orthogonal Sparse Network for Exploring Shared Knowledge in Continual Learning (ICML24)[paper]
-
<a name="todo"></a> Provable Contrastive Continual Learning (ICML24)[paper]
-
<a name="todo"></a> Gradual Divergence for Seamless Adaptation: A Novel Domain Incremental Learning Method (ICML24)[paper][code]
-
<a name="todo"></a> An Effective Dynamic Gradient Calibration Method for Continual Learning (ICML24)[paper]
-
<a name="todo"></a> Federated Continual Learning via Prompt-based Dual Knowledge Transfer (ICML24)[paper][code]
-
<a name="todo"></a> COPAL: Continual Pruning in Large Language Generative Models (ICML24)[paper]
-
<a name="todo"></a> One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning (ICML24)[paper]
-
<a name="todo"></a> Hierarchical Augmentation and Distillation for Class Incremental Audio-Visual Video Recognition (TPAMI2024)[paper]
-
<a name="todo"></a> Continual Segmentation with Disentangled Objectness Learning and Class Recognition (CVPR2024)[paper][code]
-
<a name="todo"></a> Interactive Continual Learning: Fast and Slow Thinking (CVPR2024)[paper][code]
-
<a name="todo"></a> InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning (CVPR2024)[paper][code]
-
<a name="todo"></a> Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformer (CVPR2024)[paper][code]
-
<a name="todo"></a> Traceable Federated Continual Learning (CVPR2024)[paper][code]
-
<a name="todo"></a> Defense without Forgetting: Continual Adversarial Defense with Anisotropic & Isotropic Pseudo Replay (CVPR2024)[paper]
-
<a name="todo"></a> Learning Continual Compatible Representation for Re-indexing Free Lifelong Person Re-identification (CVPR2024)[paper][code]
-
<a name="todo"></a> Towards Backward-Compatible Continual Learning of Image Compression (CVPR2024)[paper][code]
-
<a name="todo"></a> Class Incremental Learning with Multi-Teacher Distillation (CVPR2024)[paper][code]
-
<a name="todo"></a> Towards Efficient Replay in Federated Incremental Learning (CVPR2024)[paper]
-
<a name="todo"></a> Dual-consistency Model Inversion for Non-exemplar Class Incremental Learning (CVPR2024)[paper]
-
<a name="todo"></a> Dual-Enhanced Coreset Selection with Class-wise Collaboration for Online Blurry Class Incremental Learning (CVPR2024)[paper]
-
<a name="todo"></a> Coherent Temporal Synthesis for Incremental Action Segmentation (CVPR2024)[paper]
-
<a name="todo"></a> Text-Enhanced Data-free Approach for Federated Class-Incremental Learning (CVPR2024)[paper][code]
-
<a name="todo"></a> NICE: Neurogenesis Inspired Contextual Encoding for Replay-free Class Incremental Learning (CVPR2024)[paper][code]
-
<a name="todo"></a> Long-Tail Class Incremental Learning via Independent Sub-prototype Construction (CVPR2024)[paper]
-
<a name="todo"></a> FCS: Feature Calibration and Separation for Non-Exemplar Class Incremental Learning (CVPR2024)[paper][code]
-
<a name="todo"></a> Incremental Nuclei Segmentation from Histopathological Images via Future-class Awareness and Compatibility-inspired Distillation (CVPR2024)[paper][code]
-
<a name="todo"></a> Gradient Reweighting: Towards Imbalanced Class-Incremental Learning (CVPR2024)[paper][code]
-
<a name="todo"></a> OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learning (CVPR2024)[paper][code]
-
<a name="todo"></a> SDDGR: Stable Diffusion-based Deep Generative Replay for Class Incremental Object Detection (CVPR2024)[paper]
-
<a name="todo"></a> Generative Multi-modal Models are Good Class Incremental Learners (CVPR2024)[paper][code]
-
<a name="todo"></a> Task-Adaptive Saliency Guidance for Exemplar-free Class Incremental Learning (CVPR2024)[paper][code]
-
<a name="todo"></a> DYSON: Dynamic Feature Space Self-Organization for Online Task-Free Class Incremental Learning (CVPR2024)[paper][code]
-
<a name="todo"></a> Enhancing Visual Continual Learning with Language-Guided Supervision (CVPR2024)[paper]
-
<a name="todo"></a> Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters (CVPR2024)[paper][code]
-
<a name="todo"></a> Adaptive VIO: Deep Visual-Inertial Odometry with Online Continual Learning (CVPR2024)[paper]
-
<a name="todo"></a> Continual Self-supervised Learning: Towards Universal Multi-modal Medical Data Representation Learning (CVPR2024)[paper][code]
-
<a name="todo"></a> ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuning (CVPR2024)[paper][code]
-
<a name="todo"></a> Online Task-Free Continual Generative and Discriminative Learning via Dynamic Cluster Memory (CVPR2024)[paper][code]
-
<a name="todo"></a> Learning from One Continuous Video Stream (CVPR2024)[paper]
-
<a name="todo"></a> Improving Plasticity in Online Continual Learning via Collaborative Learning (CVPR2024)[paper][code]
-
<a name="todo"></a> Learning Equi-angular Representations for Online Continual Learning (CVPR2024)[paper][code]
-
<a name="todo"></a> BrainWash: A Poisoning Attack to Forget in Continual Learning (CVPR2024)[paper]
-
<a name="todo"></a> Consistent Prompting for Rehearsal-Free Continual Learning (CVPR2024)[paper][code]
-
<a name="todo"></a> Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning (CVPR2024)[paper][code]
-
<a name="todo"></a> Convolutional Prompting meets Language Models for Continual Learning (CVPR2024)[paper][code]
-
<a name="todo"></a> Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning (CVPR2024)[paper][code]
-
<a name="todo"></a> Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners (CVPR2024)[paper][code]
-
<a name="todo"></a> Orchestrate Latent Expertise: Advancing Online Continual Learning with Multi-Level Supervision and Reverse Self-Distillation (CVPR2024)[paper][code]
-
<a name="todo"></a> Elastic Feature Consolidation For Cold Start Exemplar-Free Incremental Learning (ICLR2024)[paper][code]
-
<a name="todo"></a> Function-space Parameterization of Neural Networks for Sequential Learning (ICLR2024)[paper]
-
<a name="todo"></a> Progressive Fourier Neural Representation for Sequential Video Compilation (ICLR2024)[paper]
-
<a name="todo"></a> Kalman Filter Online Classification from non-Stationary Data (ICLR2024)[paper]
-
<a name="todo"></a> Continual Momentum Filtering on Parameter Space for Online Test-time Adaptation (ICLR2024)[paper]
-
<a name="todo"></a> TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models (ICLR2024)[paper]
-
<a name="todo"></a> Class Incremental Learning via Likelihood Ratio Based Task Prediction (ICLR2024)[paper][code]
-
<a name="todo"></a> The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting - An Analytical Model (ICLR2024)[paper]
-
<a name="todo"></a> Prediction Error-based Classification for Class-Incremental Learning (ICLR2024)[paper][code]
-
<a name="todo"></a> Adapting Large Language Models via Reading Comprehension (ICLR2024)[paper][code]
-
<a name="todo"></a> Accurate Forgetting for Heterogeneous Federated Continual Learning (ICLR2024)[paper]
-
<a name="todo"></a> Fixed Non-negative Orthogonal Classifier: Inducing Zero-mean Neural Collapse with Feature Dimension Separation (ICLR2024)[paper]
-
<a name="todo"></a> A Probabilistic Framework for Modular Continual Learning (ICLR2024)[paper]
-
<a name="todo"></a> A Unified and General Framework for Continual Learning (ICLR2024)[paper]
-
<a name="todo"></a> Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation (ICLR2024)[paper]
-
<a name="todo"></a> CPPO: Continual Learning for Reinforcement Learning with Human Feedback (ICLR2024)[paper]
-
<a name="todo"></a> Online Continual Learning for Interactive Instruction Following Agents (ICLR2024)[paper][code]
-
<a name="todo"></a> Scalable Language Model with Generalized Continual Learning (ICLR2024)[paper]
-
<a name="todo"></a> ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation (ICLR2024)[paper]
-
<a name="todo"></a> Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks (ICLR2024)[paper][code]
-
<a name="todo"></a> TiC-CLIP: Continual Training of CLIP Models (ICLR2024)[paper]
-
<a name="todo"></a> Continual Learning in the Presence of Spurious Correlations: Analyses and a Simple Baseline (ICLR2024)[paper]
-
<a name="todo"></a> Addressing Catastrophic Forgetting and Loss of Plasticity in Neural Networks (ICLR2024)[paper]
-
<a name="todo"></a> Locality Sensitive Sparse Encoding for Learning World Models Online (ICLR2024)[paper]
-
<a name="todo"></a> Dissecting learning and forgetting in language model finetuning (ICLR2024)[paper]
-
<a name="todo"></a> Prompt Gradient Projection for Continual Learning (ICLR2024)[paper][code]
-
<a name="todo"></a> Latent Trajectory Learning for Limited Timestamps under Distribution Shift over Time (ICLR2024)[paper]
-
<a name="todo"></a> Divide and not forget: Ensemble of selectively trained experts in Continual Learning (ICLR2024)[paper][code]
-
<a name="todo"></a> eTag: Class-Incremental Learning via Embedding Distillation and Task-Oriented Generation (AAAI2024) [paper][code]
-
<a name="todo"></a> Evolving Parameterized Prompt Memory for Continual Learning (AAAI2024)[paper][code]
-
<a name="todo"></a> Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding (AAAI2024)[paper]
-
<a name="todo"></a> Fine-Grained Knowledge Selection and Restoration for Non-Exemplar Class Incremental Learning (AAAI2024)[paper]
-
<a name="todo"></a> Class-Incremental Learning: Cross-Class Feature Augmentation for Class Incremental Learning (AAAI2024)[paper]
-
<a name="todo"></a> Learning Task-Aware Language-Image Representation for Class-Incremental Object Detection (AAAI2024)[paper]
-
<a name="todo"></a> MIND: Multi-Task Incremental Network Distillation (AAAI2024)[paper][code]
-
<a name="todo"></a> Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual Learning (WACV2024)[paper][code]
-
<a name="todo"></a> Plasticity-Optimized Complementary Networks for Unsupervised Continual (WACV2024)[paper]
-
<a name="todo"></a> Online Class-Incremental Learning For Real-World Food Image Classification (WACV2024)[paper]
2023
- <a name="todo"></a> SIESTA: Efficient Online Continual Learning with Sleep (TMLR 2023)[paper]
- <a name="todo"></a> Sub-network Discovery and Soft-masking for Continual Learning of Mixed Tasks (EMNLP 2023)[paper]
- <a name="todo"></a > Incorporating neuro-inspired adaptability for continual learning in artificial intelligence (Nature Machine Intelligence 2023) [paper]
- <a name="todo"></a > Enhancing Knowledge Transfer for Task Incremental Learning with Data-free Subnetwork (NeurIPS 2023) [paper] [Code]
- <a name="todo"></a > Loss Decoupling for Task-Agnostic Continual Learning (NeurIPS 2023) [paper]
- <a name="todo"></a > Bilevel Coreset Selection in Continual Learning: A New Formulation and Algorithm (NeurIPS 2023)[paper]
- <a name="todo"></a > Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments (NeurIPS 2023)[paper]
- <a name="todo"></a > An Efficient Dataset Condensation Plugin and Its Application to Continual Learning (NeurIPS 2023)[paper]
- <a name="todo"></a > Overcoming Recency Bias of Normalization Statistics in Continual Learning: Balance and Adaptation (NeurIPS 2023)[paper]
- <a name="todo"></a > Prediction and Control in Continual Reinforcement Learning (NeurIPS 2023)[paper]
- <a name="todo"></a > On the Stability-Plasticity Dilemma in Continual Meta-Learning: Theory and Algorithm (NeurIPS 2023)[paper]
- <a name="todo"></a > Saving 100x Storage: Prototype Replay for Reconstructing Training Sample Distribution in Class-Incremental Semantic Segmentation (NeurIPS 2023)[paper]
- <a name="todo"></a > A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Tasks (NeurIPS 2023)[paper]
- <a name="todo"></a > Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration (NeurIPS 2023)[paper]
- <a name="todo"></a > A Unified Approach to Domain Incremental Learning with Memory: Theory and Algorithm (NeurIPS 2023)[paper][code]
- <a name="todo"></a> Minimax Forward and Backward Learning of Evolving Tasks with Performance Guarantees (NeurIPS 2023)[paper][code]
- <a name="todo"></a> Recasting Continual Learning as Sequence Modeling (NeurIPS 2023)[paper]
- <a name="todo"></a> Augmented Memory Replay-based Continual Learning Approaches for Network Intrusion Detection (NeurIPS 2023)[paper]
- <a name="todo"></a> Does Continual Learning Meet Compositionality? New Benchmarks and An Evaluation Framework (NeurIPS 2023)[paper]
- <a name="todo"></a> CL-NeRF: Continual Learning of Neural Radiance Fields for Evolving Scene Representation (NeurIPS 2023)[paper]
- <a name="todo"></a> TriRE: A Multi-Mechanism Learning Paradigm for Continual Knowledge Retention and Promotion (NeurIPS 2023)[paper]
- <a name="todo"></a> Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models (NeurIPS 2023)[paper]
- <a name="todo"></a> A Definition of Continual Reinforcement Learning (NeurIPS 2023)[paper]
- <a name="todo"></a> RanPAC: Random Projections and Pre-trained Models for Continual Learning (NeurIPS 2023)[paper]
- <a name="todo"></a> Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality (NeurIPS 2023)[paper]
- <a name="todo"></a> FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning (NeurIPS 2023)[paper]
- <a name="todo"></a> The Ideal Continual Learner: An Agent That Never Forgets (ICML2023) [paper]
- <a name="todo"></a> Continual Learners are Incremental Model Generalizers (ICML2023)[paper]
- <a name="todo"></a> Learnability and Algorithm for Continual Learning (ICML2023)[paper][code]
- <a name="todo"></a> Parameter-Level Soft-Masking for Continual Learning (ICML2023)[paper]
- <a name="todo"></a> Continual Learning in Linear Classification on Separable Data (ICML2023)[paper]
- <a name="todo"></a> DualHSIC: HSIC-Bottleneck and Alignment for Continual Learning (ICML2023)[paper]
- <a name="todo"></a> BiRT: Bio-inspired Replay in Vision Transformers for Continual Learning (ICML2023)[paper]
- <a name="todo"></a> DDGR: Continual Learning with Deep Diffusion-based Generative Replay (ICML2023)[paper]
- <a name="todo"></a> Neuro-Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept Rehearsal (ICML2023)[paper]
- <a name="todo"></a> Theory on Forgetting and Generalization of Continual Learning (ICML2023)[paper]
- <a name="todo"></a> Poisoning Generative Replay in Continual Learning to Promote Forgetting (ICML2023)[paper]
- <a name="todo"></a> Continual Vision-Language Representation Learning with Off-Diagonal Information (ICML2023)[paper]
- <a name="todo"></a> Prototype-Sample Relation Distillation: Towards Replay-Free Continual Learning (ICML2023)[paper]
- <a name="todo"></a> Does Continual Learning Equally Forget All Parameters? (ICML2023)[paper]
- <a name="todo"></a> Growing a Brain with Sparsity-Inducing Generation for Continual Learning (ICCV 2023)[paper][code]
- <a name="todo"></a> Self-regulating Prompts: Foundational Model Adaptation without Forgetting (ICCV 2023)[paper][code]
- <a name="todo"></a> Prototype Reminiscence and Augmented Asymmetric Knowledge Aggregation for Non-Exemplar Class-Incremental Learning (ICCV 2023)[paper][code]
- <a name="todo"></a> Tangent Model Composition for Ensembling and Continual Fine-tuning (ICCV 2023)[paper][code]
- <a name="todo"></a> CBA: Improving Online Continual Learning via Continual Bias Adaptor (ICCV 2023)[paper]
- <a name="todo"></a> CTP: Towards Vision-Language Continual Pretraining via Compatible Momentum Contrast and Topology Preservation (ICCV 2023)[paper][code]
- <a name="todo"></a> NAPA-VQ: Neighborhood Aware Prototype Augmentation with Vector Quantization for Continual Learning (ICCV 2023)[paper][code]
- <a name="todo"></a> Online Continual Learning on Hierarchical Label Expansion (ICCV 2023)[paper]
- <a name="todo"></a> Class-Incremental Grouping Network for Continual Audio-Visual Learning (ICCV 2023)[paper][code]
- <a name="todo"></a> Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right? (ICCV 2023)[paper][code]
- <a name="todo"></a> When Prompt-based Incremental Learning Does Not Meet Strong Pretraining (ICCV 2023)[paper]
- <a name="todo"></a> Online Class Incremental Learning on Stochastic Blurry Task Boundary via Mask and Visual Prompt Tuning (ICCV 2023)[paper][code]
- <a name="todo"></a> Dynamic Residual Classifier for Class Incremental Learning (ICCV 2023)[paper]
- <a name="todo"></a> First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learning (ICCV 2023)[paper]
- <a name="todo"></a> Masked Autoencoders are Efficient Class Incremental Learners (ICCV 2023)[paper]
- <a name="todo"></a> Introducing Language Guidance in Prompt-based Continual Learning (ICCV 2023)[paper]
- <a name="todo"></a> CLNeRF: Continual Learning Meets NeRFs (ICCV 2023)[paper]
- <a name="todo"></a> Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models (ICCV 2023)[paper][code]
- <a name="todo"></a> LFS-GAN: Lifelong Few-Shot Image Generation (ICCV 2023)[paper]
- <a name="todo"></a> TARGET: Federated Class-Continual Learning via Exemplar-Free Distillation (ICCV 2023)[paper]
- <a name="todo"></a> Learning to Learn: How to Continuously Teach Humans and Machines (ICCV 2023)[paper]
- <a name="todo"></a> Audio-Visual Class-Incremental Learning (ICCV 2023)[paper][code]
- <a name="todo"></a> MetaGCD: Learning to Continually Learn in Generalized Category Discovery (ICCV 2023)[paper]
- <a name="todo"></a> Exemplar-Free Continual Transformer with Convolutions (ICCV 2023)[paper][code]
- <a name="todo"></a> A Unified Continual Learning Framework with General Parameter-Efficient Tuning (ICCV 2023)[paper]
- <a name="todo"></a> Incremental Generalized Category Discovery (ICCV 2023)[paper]
- <a name="todo"></a> Heterogeneous Forgetting Compensation for Class-Incremental Learning (ICCV 2023)[paper][code]
- <a name="todo"></a> Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection (ICCV 2023)[paper][code]
- <a name="todo"></a> MRN: Multiplexed Routing Network for Incremental Multilingual Text Recognition (ICCV 2023)[paper][code]
- <a name="todo"></a> CLR: Channel-wise Lightweight Reprogramming for Continual Learning (ICCV 2023)[paper][code]
- <a name="todo"></a> ICICLE: Interpretable Class Incremental Continual Learning (ICCV 2023)[paper]
- <a name="todo"></a> Proxy Anchor-based Unsupervised Learning for Continuous Generalized Category Discovery (ICCV 2023)[paper]
- <a name="todo"></a> SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model (ICCV 2023)[paper][code]
- <a name="todo"></a> Online Prototype Learning for Online Continual Learning (ICCV 2023)[paper][code]
- <a name="todo"></a> Analyzing and Reducing the Performance Gap in Cross-Lingual Transfer with Fine-tuning Slow and Fast (ACL2023)[paper]
- <a name="todo"></a> Class-Incremental Learning based on Label Generation (ACL2023)[paper]
- <a name="todo"></a> Computationally Budgeted Continual Learning: What Does Matter? (CVPR2023)[paper][code]
- <a name="todo"></a> Real-Time Evaluation in Online Continual Learning: A New Hope (CVPR2023)[paper]
- <a name="todo"></a> Dealing With Cross-Task Class Discrimination in Online Continual Learning (CVPR2023)[paper][code]
- <a name="todo"></a> Decoupling Learning and Remembering: A Bilevel Memory Framework With Knowledge Projection for Task-Incremental Learning (CVPR2023)[paper][code]
- <a name="todo"></a> GKEAL: Gaussian Kernel Embedded Analytic Learning for Few-shot Class Incremental Task (CVPR2023)[paper]
- <a name="todo"></a> EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularization (CVPR2023)[paper]
- <a name="todo"></a> Endpoints Weight Fusion for Class Incremental Semantic Segmentation (CVPR2023)[paper]
- <a name="todo"></a> On the Stability-Plasticity Dilemma of Class-Incremental Learning (CVPR2023)[paper]
- <a name="todo"></a> Regularizing Second-Order Influences for Continual Learning (CVPR2023)[paper][code]
- <a name="todo"></a> Rebalancing Batch Normalization for Exemplar-based Class-Incremental Learning (CVPR2023)[paper]
- <a name="todo"></a> Task Difficulty Aware Parameter Allocation & Regularization for Lifelong Learning (CVPR2023)[paper]
- <a name="todo"></a> A Probabilistic Framework for Lifelong Test-Time Adaptation (CVPR2023)[paper][code]
- <a name="todo"></a> Continual Semantic Segmentation with Automatic Memory Sample Selection (CVPR2023)[paper]
- <a name="todo"></a> Exploring Data Geometry for Continual Learning (CVPR2023)[paper]
- <a name="todo"></a> PCR: Proxy-based Contrastive Replay for Online Class-Incremental Continual Learning (CVPR2023)[paper][code]
- <a name="todo"></a> Learning with Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learning (CVPR2023)[paper][code]
- <a name="todo"></a> Foundation Model Drives Weakly Incremental Learning for Semantic Segmentation (CVPR2023)[paper]
- <a name="todo"></a> Continual Detection Transformer for Incremental Object Detection (CVPR2023)[paper][code]
- <a name="todo"></a> PIVOT: Prompting for Video Continual Learning (CVPR2023)[paper]
- <a name="todo"></a> CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning (CVPR2023)[paper][code]
- <a name="todo"></a> Principles of Forgetting in Domain-Incremental Semantic Segmentation in Adverse Weather Conditions (CVPR2023)[paper]
- <a name="todo"></a> Class-Incremental Exemplar Compression for Class-Incremental Learning (CVPR2023)[paper][code]
- <a name="todo"></a> Dense Network Expansion for Class Incremental Learning (CVPR2023)[paper]
- <a name="todo"></a> Online Bias Correction for Task-Free Continual Learning (ICLR2023)[paper]
- <a name="todo"></a> Sparse Distributed Memory is a Continual Learner (ICLR2023)[paper]
- <a name="todo"></a> Continual Learning of Language Models (ICLR2023)[paper]
- <a name="todo"></a> Progressive Prompts: Continual Learning for Language Models without Forgetting (ICLR2023)[paper]
- <a name="todo"></a> Is Forgetting Less a Good Inductive Bias for Forward Transfer? (ICLR2023)[paper]
- <a name="todo"></a> Online Boundary-Free Continual Learning by Scheduled Data Prior (ICLR2023)[paper]
- <a name="todo"></a>Incremental Learning of Structured Memory via Closed-Loop Transcription (ICLR2023)[paper]
- <a name="todo"></a>Better Generative Replay for Continual Federated Learning (ICLR2023)[paper]
- <a name="todo"></a>3EF: Class-Incremental Learning via Efficient Energy-Based Expansion and Fusion (ICLR2023)[paper]
- <a name="todo"></a>Progressive Voronoi Diagram Subdivision Enables Accurate Data-free Class-Incremental Learning (ICLR2023)[paper]
- <a name="todo"></a>Learning without Prejudices: Continual Unbiased Learning via Benign and Malignant Forgetting (ICLR2023)[paper]
- <a name="todo"></a>Building a Subspace of Policies for Scalable Continual Learning (ICLR2023)[paper]
- <a name="todo"></a>A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning (ICLR2023)[paper]
- <a name="todo"></a>Continual evaluation for lifelong learning: Identifying the stability gap (ICLR2023)[paper]
- <a name="todo"></a>Continual Unsupervised Disentangling of Self-Organizing Representations (ICLR2023)[paper]
- <a name="todo"></a>Warping the Space: Weight Space Rotation for Class-Incremental Few-Shot Learning (ICLR2023)[paper]
- <a name="todo"></a>Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental Learning (ICLR2023)[paper]
- <a name="todo"></a>On the Soft-Subnetwork for Few-Shot Class Incremental Learning (ICLR2023)[paper]
- <a name="todo"></a>Task-Aware Information Routing from Common Representation Space in Lifelong Learning (ICLR2023)[paper]
- <a name="todo"></a>Error Sensitivity Modulation based Experience Replay: Mitigating Abrupt Representation Drift in Continual Learning (ICLR2023)[paper]
- <a name="todo"></a> Neural Weight Search for Scalable Task Incremental Learning (WACV2023)[paper]
- <a name="todo"></a> Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentation (WACV2023)[paper]
- <a name="todo"></a> FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning (WACV2023)[paper]
- <a name="todo"></a> Do Pre-trained Models Benefit Equally in Continual Learning? (WACV2023)[paper] [code]
- <a name="todo"></a> Sparse Coding in a Dual Memory System for Lifelong Learning (AAAI2023)[paper] [code]
2022
-
<a name="todo"></a> Online Continual Learning through Mutual Information Maximization (ICML2022)[paper]
-
<a name="todo"></a> Prototype-guided continual adaptation for class-incremental unsupervised domain adaptation (ECCV2022)[paper] [code]
-
<a name="todo"></a> Balanced softmax cross-entropy for incremental learning with and without memory (CVIU)[paper]
-
<a name="todo"></a> Incremental Prompting: Episodic Memory Prompt for Lifelong Event Detection (COLING2022) [paper] [code]
-
<a name="todo"></a> Improving Task-free Continual Learning by Distributionally Robust Memory Evolution (ICML2022)[paper]
-
<a name="todo"></a> Forget-free Continual Learning with Winning Subnetworks (ICML2022)[paper]
-
<a name="todo"></a> NISPA: Neuro-Inspired Stability-Plasticity Adaptation for Continual Learning in Sparse Networks (ICML2022)[paper]
-
<a name="todo"></a> Continual Learning via Sequential Function-Space Variational Inference (ICML2022)[paper]
-
<a name="todo"></a> A Theoretical Study on Solving Continual Learning (NeurIPS2022) [paper] [code]
-
<a name="todo"></a> ACIL: Analytic Class-Incremental Learning with Absolute Memorization and Privacy Protection (NeurIPS2022) [paper]
-
<a name="todo"></a> Beyond Not-Forgetting: Continual Learning with Backward Knowledge Transfer (NeurIPS2022) [paper]
-
<a name="todo"></a> Memory Efficient Continual Learning with Transformers (NeurIPS2022) [paper]
-
<a name="todo"></a> Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation (NeurIPS2022) [paper] [code]
-
<a name="todo"></a> Disentangling Transfer in Continual Reinforcement Learning (NeurIPS2022) [paper]
-
<a name="todo"></a> Task-Free Continual Learning via Online Discrepancy Distance Learning (NeurIPS2022) [paper]
-
<a name="todo"></a> A simple but strong baseline for online continual learning: Repeated Augmented Rehearsal (NeurIPS2022) [paper]
-
<a name="todo"></a> S-Prompts Learning with Pre-trained Transformers: An Occam’s Razor for Domain Incremental Learning (NeurIPS2022) [paper]
-
<a name="todo"></a> Lifelong Neural Predictive Coding: Learning Cumulatively Online without Forgetting (NeurIPS2022) [paper]
-
<a name="todo"></a> Few-Shot Continual Active Learning by a Robot (NeurIPS2022) [paper]
-
<a name="todo"></a> Continual learning: a feature extraction formalization, an efficient algorithm, and fundamental obstructions(NeurIPS2022) [paper]
-
<a name="todo"></a> SparCL: Sparse Continual Learning on the Edge(NeurIPS2022) [paper]
-
<a name="todo"></a> CLiMB: A Continual Learning Benchmark for Vision-and-Language Tasks (NeurIPS2022) [paper] [code]
-
<a name="todo"></a> Continual Learning In Environments With Polynomial Mixing Times (NeurIPS2022) [paper] [code]
-
<a name="todo"></a> Exploring Example Influence in Continual Learning (NeurIPS2022) [paper] [code]
-
<a name="todo"></a> ALIFE: Adaptive Logit Regularizer and Feature Replay for Incremental Semantic Segmentation (NeurIPS2022) [paper]
-
<a name="todo"></a> On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learning (NeurIPS2022) [paper] [code]
-
<a name="todo"></a> On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting (NeurIPS2022)[paper]
-
<a name="todo"></a> CGLB: Benchmark Tasks for Continual Graph Learning (NeurIPS2022)[paper] [code]
-
<a name="todo"></a> How Well Do Unsupervised Learning Algorithms Model Human Real-time and Life-long Learning? (NeurIPS2022)[paper]
-
<a name="todo"></a> CoSCL: Cooperation of Small Continual Learners is Stronger than a Big One (ECCV2022)[paper] [code]
-
<a name="todo"></a>Generative Negative Text Replay for Continual Vision-Language Pretraining (ECCV2022) [paper]
-
<a name="todo"></a> DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning (ECCV2022) [paper] [code]
-
<a name="todo"></a> The Challenges of Continuous Self-Supervised Learning (ECCV2022)[paper]
-
<a name="todo"></a> Helpful or Harmful: Inter-Task Association in Continual Learning (ECCV2022)[paper]
-
<a name="todo"></a> incDFM: Incremental Deep Feature Modeling for Continual Novelty Detection (ECCV2022)[paper]
-
<a name="todo"></a> S3C: Self-Supervised Stochastic Classifiers for Few-Shot Class-Incremental Learning (ECCV2022)[paper]
-
<a name="todo"></a> Online Task-free Continual Learning with Dynamic Sparse Distributed Memory (ECCV2022)[paper][code]
-
<a name="todo"></a> Balancing between Forgetting and Acquisition in Incremental Subpopulation Learning (ECCV2022)[paper]
-
<a name="todo"></a> Class-Incremental Learning with Cross-Space Clustering and Controlled Transfer (ECCV2022) [paper] [code]
-
<a name="todo"></a> FOSTER: Feature Boosting and Compression for Class-Incremental Learning (ECCV2022) [paper] [code]
-
<a name="todo"></a> Meta-Learning with Less Forgetting on Large-Scale Non-Stationary Task Distributions (ECCV2022) [paper]
-
<a name="todo"></a> R-DFCIL: Relation-Guided Representation Learning for Data-Free Class Incremental Learning (ECCV2022) [paper] [code]
-
<a name="todo"></a> DLCFT: Deep Linear Continual Fine-Tuning for General Incremental Learning (ECCV2022) [paper]
-
<a name="todo"></a> Learning with Recoverable Forgetting (ECCV2022) [paper]
-
<a name="todo"></a> Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation (ECCV2022) [paper] [code]
-
<a name="todo"></a> Balancing Stability and Plasticity through Advanced Null Space in Continual Learning (ECCV2022) [paper]
-
<a name="todo"></a>Long-Tailed Class Incremental Learning (ECCV2022) [paper]
-
<a name="todo"></a>Anti-Retroactive Interference for Lifelong Learning (ECCV2022) [paper]
-
<a name="todo"></a>Novel Class Discovery without Forgetting (ECCV2022) [paper]
-
<a name="todo"></a>Class-incremental Novel Class Discovery (ECCV2022) [paper]
-
<a name="todo"></a>Few-Shot Class Incremental Learning From an Open-Set Perspective(ECCV2022)[paper]
-
<a name="todo"></a>Incremental Task Learning with Incremental Rank Updates(ECCV2022)[paper]
-
<a name="todo"></a>Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay(ECCV2022)[paper]
-
<a name="todo"></a>Online Continual Learning with Contrastive Vision Transformer (ECCV2022)[paper]
-
<a name="todo"></a>Transfer without Forgetting (ECCV2022) [paper][code]
-
<a name="todo"></a> Continual Training of Language Models for Few-Shot Learning (EMNLP2022) [paper] [code]
-
<a name="todo"></a> Uncertainty-aware Contrastive Distillation for Incremental Semantic Segmentation (TPAMI2022) [paper]
-
<a name="todo"></a> MgSvF: Multi-Grained Slow vs. Fast Framework for Few-Shot Class-Incremental Learning (TPAMI2022) [paper]
-
<a name="todo"></a>Class-Incremental Continual Learning into the eXtended DER-verse (TPAMI2022) [paper] [code]
-
<a name="todo"></a>Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks (TPAMI2022) [paper] [code]
-
<a name="todo"></a>Continual Semi-Supervised Learning through Contrastive Interpolation Consistency (PRL2022) [paper][code]
-
<a name="todo"></a>GCR: Gradient Coreset Based Replay Buffer Selection for Continual Learning (CVPR2022) [paper]
-
<a name="todo"></a>Learning Bayesian Sparse Networks With Full Experience Replay for Continual Learning (CVPR2022) [paper]
-
<a name="todo"></a>Continual Learning With Lifelong Vision Transformer (CVPR2022) [paper]
-
<a name="todo"></a>Towards Better Plasticity-Stability Trade-Off in Incremental Learning: A Simple Linear Connector (CVPR2022) [paper]
-
<a name="todo"></a>Doodle It Yourself: Class Incremental Learning by Drawing a Few Sketches (CVPR2022) [paper]
-
<a name="todo"></a>Continual Learning for Visual Search with Backward Consistent Feature Embedding (CVPR2022) [paper]
-
<a name="todo"></a>Online Continual Learning on a Contaminated Data Stream with Blurry Task Boundaries (CVPR2022) [paper]
-
<a name="todo"></a>Not Just Selection, but Exploration: Online Class-Incremental Continual Learning via Dual View Consistency (CVPR2022) [paper]
-
<a name="todo"></a>Bring Evanescent Representations to Life in Lifelong Class Incremental Learning (CVPR2022) [paper]
-
<a name="todo"></a>Lifelong Graph Learning (CVPR2022) [paper]
-
<a name="todo"></a>Lifelong Unsupervised Domain Adaptive Person Re-identification with Coordinated Anti-forgetting and Adaptation (CVPR2022) [paper]
-
<a name="todo"></a>vCLIMB: A Novel Video Class Incremental Learning Benchmark (CVPR2022) [paper]
-
<a name="todo"></a>Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidation(CVPR2022) [paper]
-
<a name="todo"></a>Few-Shot Incremental Learning for Label-to-Image Translation (CVPR2022) [paper]
-
<a name="todo"></a> MetaFSCIL: A Meta-Learning Approach for Few-Shot Class Incremental Learning (CVPR2022) [paper]
-
<a name="todo"></a> Incremental Learning in Semantic Segmentation from Image Labels (CVPR2022) [paper]
-
<a name="todo"></a> Self-Supervised Models are Continual Learners (CVPR2022) [paper] [code]
-
<a name="todo"></a> Learning to Imagine: Diversify Memory for Incremental Learning using Unlabeled Data (CVPR2022) [paper]
-
<a name="todo"></a> General Incremental Learning with Domain-aware Categorical Representations (CVPR2022) [paper]
-
<a name="todo"></a> Constrained Few-shot Class-incremental Learning (CVPR2022) [paper]
-
<a name="todo"></a> Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillation (CVPR2022) [paper]
-
<a name="todo"></a> Class-Incremental Learning with Strong Pre-trained Models (CVPR2022) [paper]
-
<a name="todo"></a> Energy-based Latent Aligner for Incremental Learning (CVPR2022) [paper] [code]
-
<a name="todo"></a> Meta-attention for ViT-backed Continual Learning (CVPR2022) [paper] [code]
-
<a name="todo"></a> Learning to Prompt for Continual Learning (CVPR2022) [paper] [code]
-
<a name="todo"></a> On Generalizing Beyond Domains in Cross-Domain Continual Learning (CVPR2022) [paper]
-
<a name="todo"></a> Probing Representation Forgetting in Supervised and Unsupervised Continual Learning (CVPR2022) [paper]
-
<a name="todo"></a> Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding (CVPR2022) [paper] [code]
-
<a name="todo"></a> Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning (CVPR2022) [paper] [code]
-
<a name="todo"></a> Forward Compatible Few-Shot Class-Incremental Learning (CVPR2022) [paper] [code]
-
<a name="todo"></a> Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning (CVPR2022) [paper]
-
<a name="todo"></a> DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion (CVPR2022) [paper]
-
<a name="todo"></a> Federated Class-Incremental Learning (CVPR2022) [paper] [code]
-
<a name="todo"></a> Representation Compensation Networks for Continual Semantic Segmentation (CVPR2022) [paper]
-
<a name="todo"></a> A Multi-Head Model for Continual Learning via Out-of-Distribution Replay (CoLLAs2022) [paper] [code]
-
<a name="todo"></a> Continual Attentive Fusion for Incremental Learning in Semantic Segmentation (TMM2022) [paper]
-
<a name="todo"></a> Self-training for class-incremental semantic segmentation (TNNLS2022) [paper]
-
<a name="todo"></a> Effects of Auxiliary Knowledge on Continual Learning (ICPR2022) [paper]
-
<a name="todo"></a>Continual Sequence Generation with Adaptive Compositional Modules (ACL2022) [paper]
-
<a name="todo"></a> Learngene: From Open-World to Your Learning Task (AAAI2022) [paper] [code]
-
<a name="todo"></a> Rethinking the Representational Continuity: Towards Unsupervised Continual Learning (ICLR2022) [paper]
-
<a name="todo"></a> Continual Learning with Filter Atom Swapping (ICLR2022) [paper]
-
<a name="todo"></a> Continual Learning with Recursive Gradient Optimization (ICLR2022) [paper]
-
<a name="todo"></a> TRGP: Trust Region Gradient Projection for Continual Learning (ICLR2022) [paper]
-
<a name="todo"></a> Looking Back on Learned Experiences For Class/task Incremental Learning (ICLR2022) [paper]
-
<a name="todo"></a> Continual Normalization: Rethinking Batch Normalization for Online Continual Learning (ICLR2022) [paper]
-
<a name="todo"></a> Model Zoo: A Growing Brain That Learns Continually (ICLR2022) [paper]
-
<a name="todo"></a> Learning curves for continual learning in neural networks: Self-knowledge transfer and forgetting (ICLR2022) [paper]
-
<a name="todo"></a> Memory Replay with Data Compression for Continual Learning (ICLR2022) [paper]
-
<a name="todo"></a> Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System (ICLR2022) [paper]
-
<a name="todo"></a> Online Coreset Selection for Rehearsal-based Continual Learning (ICLR2022) [paper]
-
<a name="todo"></a> Pretrained Language Model in Continual Learning: A Comparative Study (ICLR2022) [paper]
-
<a name="todo"></a> Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference (ICLR2022) [paper]
-
<a name="todo"></a> New Insights on Reducing Abrupt Representation Change in Online Continual Learning (ICLR2022) [paper]
-
<a name="todo"></a> Towards Continual Knowledge Learning of Language Models (ICLR2022) [paper]
-
<a name="todo"></a> CLEVA-Compass: A Continual Learning Evaluation Assessment Compass to Promote Research Transparency and Comparability (ICLR2022) [paper]
-
<a name="todo"></a> CoMPS: Continual Meta Policy Search (ICLR2022) [paper]
-
<a name="todo"></a> Information-theoretic Online Memory Selection for Continual Learning (ICLR2022) [paper]
-
<a name="todo"></a> Subspace Regularizers for Few-Shot Class Incremental Learning (ICLR2022) [paper]
-
<a name="todo"></a> LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5 (ICLR2022) [paper]
-
<a name="todo"></a> Effect of scale on catastrophic forgetting in neural networks (ICLR2022) [paper]
-
<a name="todo"></a> Dataset Knowledge Transfer for Class-Incremental Learning without Memory (WACV2022) [paper]
-
<a name="todo"></a> Knowledge Capture and Replay for Continual Learning (WACV2022) [paper]
-
<a name="todo"></a> Online Continual Learning via Candidates Voting (WACV2022) [paper]
-
<a name="todo"></a> lpSpikeCon: Enabling Low-Precision Spiking Neural Network Processing for Efficient Unsupervised Continual Learning on Autonomous Agents (IJCNN2022) [paper]
-
<a name="todo"></a> Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition (Journal of Imaging 2022) [paper]
2021
- <a name="todo"></a> Incremental Object Detection via Meta-Learning (TPAMI 2021) [paper] [code]
- <a name="todo"></a> Triple-Memory Networks: A Brain-Inspired Method for Continual Learning (TNNLS 2021) [paper]
- <a name="todo"></a> Memory efficient class-incremental learning for image classification (TNNLS 2021) [paper]
- <a name="todo"></a> A Procedural World Generation Framework for Systematic Evaluation of Continual Learning (NeurIPS2021) [paper]
- <a name="todo"></a> Class-Incremental Learning via Dual Augmentation (NeurIPS2021) [paper]
- <a name="todo"></a> SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning (NeurIPS2021) [paper]
- <a name="todo"></a> RMM: Reinforced Memory Management for Class-Incremental Learning (NeurIPS2021) [paper]
- <a name="todo"></a> Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima (NeurIPS2021) [paper]
- <a name="todo"></a> Lifelong Domain Adaptation via Consolidated Internal Distribution (NeurIPS2021) [paper]
- <a name="todo"></a> AFEC: Active Forgetting of Negative Transfer in Continual Learning (NeurIPS2021) [paper]
- <a name="todo"></a> Natural continual learning: success is a journey, not (just) a destination (NeurIPS2021) [paper]
- <a name="todo"></a> Gradient-based Editing of Memory Examples for Online Task-free Continual Learning (NeurIPS2021) [paper]
- <a name="todo"></a> Optimizing Reusable Knowledge for Continual Learning via Metalearning (NeurIPS2021) [paper]
- <a name="todo"></a> Formalizing the Generalization-Forgetting Trade-off in Continual Learning (NeurIPS2021) [paper]
- <a name="todo"></a> Learning where to learn: Gradient sparsity in meta and continual learning (NeurIPS2021) [paper]
- <a name="todo"></a> Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learning (NeurIPS2021) [paper]
- <a name="todo"></a> Posterior Meta-Replay for Continual Learning (NeurIPS2021) [paper]
- <a name="todo"></a> Continual Auxiliary Task Learning (NeurIPS2021) [paper]
- <a name="todo"></a> Mitigating Forgetting in Online Continual Learning with Neuron Calibration (NeurIPS2021) [paper]
- <a name="todo"></a> BNS: Building Network Structures Dynamically for Continual Learning (NeurIPS2021) [paper]
- <a name="todo"></a> DualNet: Continual Learning, Fast and Slow (NeurIPS2021) [paper]
- <a name="todo"></a> BooVAE: Boosting Approach for Continual Learning of VAE (NeurIPS2021) [paper]
- <a name="todo"></a> Generative vs. Discriminative: Rethinking The Meta-Continual Learning (NeurIPS2021) [paper]
- <a name="todo"></a> Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning (NeurIPS2021) [paper]
- <a name="todo"></a> Bridging Non Co-occurrence with Unlabeled In-the-wild Data for Incremental Object Detection (NeurIPS, 2021) [paper] [code]
- <a name="todo"></a> SS-IL: Separated Softmax for Incremental Learning (ICCV, 2021) [paper]
- <a name="todo"></a> Striking a Balance between Stability and Plasticity for Class-Incremental Learning (ICCV, 2021) [paper]
- <a name="todo"></a> Synthesized Feature based Few-Shot Class-Incremental Learning on a Mixture of Subspaces (ICCV, 2021) [paper]
- <a name="todo"></a> Class-Incremental Learning for Action Recognition in Videos (ICCV, 2021) [paper]
- <a name="todo"></a> Continual Prototype Evolution:Learning Online from Non-Stationary Data Streams (ICCV, 2021) [paper]
- <a name="todo"></a> Rehearsal Revealed: The Limits and Merits of Revisiting Samples in Continual Learning (ICCV, 2021) [paper]
- <a name="todo"></a> Co2L: Contrastive Continual Learning (ICCV, 2021) [paper]
- <a name="todo"></a> Wanderlust: Online Continual Object Detection in the Real World (ICCV, 2021) [paper]
- <a name="todo"></a> Continual Learning on Noisy Data Streams via Self-Purified Replay (ICCV, 2021) [paper]
- <a name="todo"></a> Else-Net: Elastic Semantic Network for Continual Action Recognition from Skeleton Data (ICCV, 2021) [paper]
- <a name="todo"></a> Detection and Continual Learning of Novel Face Presentation Attacks (ICCV, 2021) [paper]
- <a name="todo"></a> Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Data (ICCV, 2021) [paper]
- <a name="todo"></a> Continual Learning for Image-Based Camera Localization (ICCV, 2021) [paper]
- <a name="todo"></a> Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgetting (ICCV, 2021) [paper]
- <a name="todo"></a> Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning (ICCV, 2021) [paper]
- <a name="todo"></a> RECALL: Replay-based Continual Learning in Semantic Segmentation (ICCV, 2021) [paper]
- <a name="todo"></a> Few-Shot and Continual Learning with Attentive Independent Mechanisms (ICCV, 2021) [paper]
- <a name="todo"></a> Learning with Selective Forgetting (IJCAI, 2021) [paper]
- <a name="todo"></a> Continuous Coordination As a Realistic Scenario for Lifelong Learning (ICML, 2021) [paper]
- <a name="todo"></a> Kernel Continual Learning (ICML, 2021) [paper]
- <a name="todo"></a> Variational Auto-Regressive Gaussian Processes for Continual Learning (ICML, 2021) [paper]
- <a name="todo"></a> Bayesian Structural Adaptation for Continual Learning (ICML, 2021) [paper]
- <a name="todo"></a> Continual Learning in the Teacher-Student Setup: Impact of Task Similarity (ICML, 2021) [paper]
- <a name="todo"></a> Continuous Coordination As a Realistic Scenario for Lifelong Learning (ICML, 2021) [paper]
- <a name="todo"></a> Federated Continual Learning with Weighted Inter-client Transfer (ICML, 2021) [paper]
- <a name="todo"></a> Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks (NAACL, 2021) [paper]
- <a name="todo"></a> Continual Learning for Text Classification with Information Disentanglement Based Regularization (NAACL, 2021) [paper]
- <a name="todo"></a> CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks (EMNLP, 2021) [paper][code]
- <a name="todo"></a> Co-Transport for Class-Incremental Learning (ACM MM, 2021) [paper]
- <a name="todo"></a> Towards Open World Object Detection (CVPR, 2021) [paper] [code] [video]
- <a name="todo"></a> Prototype Augmentation and Self-Supervision for Incremental Learning (CVPR, 2021) [paper] [code]
- <a name="todo"></a> ORDisCo: Effective and Efficient Usage of Incremental Unlabeled Data for Semi-supervised Continual Learning (CVPR, 2021) [paper]
- <a name="todo"></a> Incremental Learning via Rate Reduction (CVPR, 2021) [paper]
- <a name="todo"></a> IIRC: Incremental Implicitly-Refined Classification (CVPR, 2021) [paper]
- <a name="todo"></a> Continual Adaptation of Visual Representations via Domain Randomization and Meta-learning (CVPR, 2021) [paper]
- <a name="todo"></a> Image De-raining via Continual Learning (CVPR, 2021) [paper]
- <a name="todo"></a> Continual Learning via Bit-Level Information Preserving (CVPR, 2021) [paper]
- <a name="todo"></a> Hyper-LifelongGAN: Scalable Lifelong Learning for Image Conditioned Generation (CVPR, 2021) [paper]
- <a name="todo"></a> Lifelong Person Re-Identification via Adaptive Knowledge Accumulation (CVPR, 2021) [paper]
- <a name="todo"></a> Distilling Causal Effect of Data in Class-Incremental Learning (CVPR, 2021) [paper]
- <a name="todo"></a> Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning (CVPR, 2021) [paper]
- <a name="todo"></a> Layerwise Optimization by Gradient Decomposition for Continual Learning (CVPR, 2021) [paper]
- <a name="todo"></a> Adaptive Aggregation Networks for Class-Incremental Learning (CVPR, 2021) [paper]
- <a name="todo"></a> Incremental Few-Shot Instance Segmentation (CVPR, 2021) [paper]
- <a name="todo"></a> Efficient Feature Transformations for Discriminative and Generative Continual Learning (CVPR, 2021) [paper]
- <a name="todo"></a> On Learning the Geodesic Path for Incremental Learning (CVPR, 2021) [paper]
- <a name="todo"></a> Few-Shot Incremental Learning with Continually Evolved Classifiers (CVPR, 2021) [paper]
- <a name="todo"></a> Rectification-based Knowledge Retention for Continual Learning (CVPR, 2021) [paper]
- <a name="todo"></a> DER: Dynamically Expandable Representation for Class Incremental Learning (CVPR, 2021) [paper]
- <a name="todo"></a> Rainbow Memory: Continual Learning with a Memory of Diverse Samples (CVPR, 2021) [paper]
- <a name="todo"></a> Training Networks in Null Space of Feature Covariance for Continual Learning (CVPR, 2021) [paper]
- <a name="todo"></a> Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning (CVPR, 2021) [paper]
- <a name="todo"></a> PLOP: Learning without Forgetting for Continual Semantic Segmentation (CVPR, 2021) [paper]
- <a name="todo"></a> Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations (CVPR, 2021) [paper]
- <a name="todo"></a> Online Class-Incremental Continual Learning with Adversarial Shapley Value(AAAI, 2021) [paper] [code]
- <a name="todo"></a> Lifelong and Continual Learning Dialogue Systems: Learning during Conversation(AAAI, 2021) [paper]
- <a name="todo"></a> Continual learning for named entity recognition(AAAI, 2021) [paper]
- <a name="todo"></a> Using Hindsight to Anchor Past Knowledge in Continual Learning(AAAI, 2021) [paper]
- <a name="todo"></a> Split-and-Bridge: Adaptable Class Incremental Learning within a Single Neural Network(AAAI, 2021) [paper] [code]
- <a name="todo"></a> Curriculum-Meta Learning for Order-Robust Continual Relation Extraction(AAAI, 2021) [paper]
- <a name="todo"></a> Continual Learning by Using Information of Each Class Holistically(AAAI, 2021) [paper]
- <a name="todo"></a> Gradient Regularized Contrastive Learning for Continual Domain Adaptation(AAAI, 2021) [paper]
- <a name="todo"></a> Unsupervised Model Adaptation for Continual Semantic Segmentation(AAAI, 2021) [paper]
- <a name="todo"></a> A Continual Learning Framework for Uncertainty-Aware Interactive Image Segmentation(AAAI, 2021) [paper]
- <a name="todo"></a> Do Not Forget to Attend to Uncertainty While Mitigating Catastrophic Forgetting(WACV, 2021) [paper]
- <a name="todo"></a> SpikeDyn: A Framework for Energy-Efficient Spiking Neural Networks with Continual and Unsupervised Learning Capabilities in Dynamic Environments (DAC2021) [paper]
2020
- <a name="todo"></a> Rethinking Experience Replay: a Bag of Tricks for Continual Learning(ICPR, 2020) [paper] [code]
- <a name="todo"></a> Continual Learning for Natural Language Generation in Task-oriented Dialog Systems(EMNLP, 2020) [paper]
- <a name="todo"></a> Distill and Replay for Continual Language Learning(COLING, 2020) [paper]
- <a name="todo"></a> Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks (NeurIPS2020) [paper] [code]
- <a name="todo"></a> Meta-Consolidation for Continual Learning (NeurIPS2020) [paper]
- <a name="todo"></a> Understanding the Role of Training Regimes in Continual Learning (NeurIPS2020) [paper]
- <a name="todo"></a> Continual Learning with Node-Importance based Adaptive Group Sparse Regularization (NeurIPS2020) [paper]
- <a name="todo"></a> Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning (NeurIPS2020) [paper]
- <a name="todo"></a> Coresets via Bilevel Optimization for Continual Learning and Streaming (NeurIPS2020) [paper]
- <a name="todo"></a> RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning (NeurIPS2020) [paper]
- <a name="todo"></a> Continual Deep Learning by Functional Regularisation of Memorable Past (NeurIPS2020) [paper]
- <a name="todo"></a> Dark Experience for General Continual Learning: a Strong, Simple Baseline (NeurIPS2020) [paper] [code]
- <a name="todo"></a> GAN Memory with No Forgetting (NeurIPS2020) [paper]
- <a name="todo"></a> Calibrating CNNs for Lifelong Learning (NeurIPS2020) [paper]
- <a name="todo"></a> Mitigating Forgetting in Online Continual Learning via Instance-Aware Parameterization (NeurIPS2020) [paper]
- <a name="todo"></a> ADER: Adaptively Distilled Exemplar Replay Towards Continual Learning for Session-based Recommendation(RecSys, 2020) [paper]
- <a name="todo"></a> Initial Classifier Weights Replay for Memoryless Class Incremental Learning (BMVC2020) [paper]
- <a name="todo"></a> Adversarial Continual Learning (ECCV2020) [paper] [code]
- <a name="todo"></a> REMIND Your Neural Network to Prevent Catastrophic Forgetting (ECCV2020) [paper] [code]
- <a name="todo"></a> Incremental Meta-Learning via Indirect Discriminant Alignment (ECCV2020) [paper]
- <a name="todo"></a> Memory-Efficient Incremental Learning Through Feature Adaptation (ECCV2020) [paper]
- <a name="todo"></a> PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning (ECCV2020) [paper] [code]
- <a name="todo"></a> Reparameterizing Convolutions for Incremental Multi-Task Learning Without Task Interference (ECCV2020) [paper]
- <a name="todo"></a> Learning latent representions across multiple data domains using Lifelong VAEGAN (ECCV2020) [paper]
- <a name="todo"></a> Online Continual Learning under Extreme Memory Constraints (ECCV2020) [paper]
- <a name="todo"></a> Class-Incremental Domain Adaptation (ECCV2020) [paper]
- <a name="todo"></a> More Classifiers, Less Forgetting: A Generic Multi-classifier Paradigm for Incremental Learning (ECCV2020) [paper]
- <a name="todo"></a> Piggyback GAN: Efficient Lifelong Learning for Image Conditioned Generation (ECCV2020) [paper]
- <a name="todo"></a> GDumb: A Simple Approach that Questions Our Progress in Continual Learning (ECCV2020) [paper]
- <a name="todo"></a> Imbalanced Continual Learning with Partitioning Reservoir Sampling (ECCV2020) [paper]
- <a name="todo"></a> Topology-Preserving Class-Incremental Learning (ECCV2020) [paper]
- <a name="todo"></a> GraphSAIL: Graph Structure Aware Incremental Learning for Recommender Systems (CIKM2020) [paper]
- <a name="todo"></a> OvA-INN: Continual Learning with Invertible Neural Networks (IJCNN2020) [paper]
- <a name="todo"></a> XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning (ICLM2020) [paper]
- <a name="todo"></a> Optimal Continual Learning has Perfect Memory and is NP-HARD (ICML2020) [paper]
- <a name="todo"></a> Neural Topic Modeling with Continual Lifelong Learning (ICML2020) [paper]
- <a name="todo"></a> Continual Learning with Knowledge Transfer for Sentiment Classification (ECML-PKDD2020) [paper] [code]
- <a name="todo"></a> Semantic Drift Compensation for Class-Incremental Learning (CVPR2020) [paper] [code]
- <a name="todo"></a> Few-Shot Class-Incremental Learning (CVPR2020) [paper]
- <a name="todo"></a> Modeling the Background for Incremental Learning in Semantic Segmentation (CVPR2020) [paper]
- <a name="todo"></a> Incremental Few-Shot Object Detection (CVPR2020) [paper]
- <a name="todo"></a> Incremental Learning In Online Scenario (CVPR2020) [paper]
- <a name="todo"></a> Maintaining Discrimination and Fairness in Class Incremental Learning (CVPR2020) [paper]
- <a name="todo"></a> Conditional Channel Gated Networks for Task-Aware Continual Learning (CVPR2020) [paper]
- <a name="todo"></a> Continual Learning with Extended Kronecker-factored Approximate Curvature (CVPR2020) [paper]
- <a name="todo"></a> iTAML : An Incremental Task-Agnostic Meta-learning Approach (CVPR2020) [paper] [code]
- <a name="todo"></a> Mnemonics Training: Multi-Class Incremental Learning without Forgetting (CVPR2020) [paper] [code]
- <a name="todo"></a> ScaIL: Classifier Weights Scaling for Class Incremental Learning (WACV2020) [paper]
- <a name="todo"></a> Accepted papers(ICLR2020) [paper]
- <a name="todo"></a> Brain-inspired replay for continual learning with artificial neural networks (Natrue Communications 2020) [paper] [code]
- <a name="todo"></a> Learning to Continually Learn (ECAI 2020) [paper] [code]
2019
- <a name="todo"></a> Compacting, Picking and Growing for Unforgetting Continual Learning (NeurIPS2019)[paper][code]
- <a name="todo"></a> Increasingly Packing Multiple Facial-Informatics Modules in A Unified Deep-Learning Model via Lifelong Learning (ICMR2019) [paper][code]
- <a name="todo"></a> Towards Training Recurrent Neural Networks for Lifelong Learning (Neural Computation 2019) [paper]
- <a name="todo"></a> Complementary Learning for Overcoming Catastrophic Forgetting Using Experience Replay (IJCAI2019) [paper]
- <a name="todo"></a> IL2M: Class Incremental Learning With Dual Memory (ICCV2019) [paper]
- <a name="todo"></a> Incremental Learning Using Conditional Adversarial Networks (ICCV2019) [paper]
- <a name="todo"></a> Adaptive Deep Models for Incremental Learning: Considering Capacity Scalability and Sustainability (KDD2019) [paper]
- <a name="todo"></a> Random Path Selection for Incremental Learning (NeurIPS2019) [paper]
- <a name="todo"></a> Online Continual Learning with Maximal Interfered Retrieval (NeurIPS2019) [paper]
- <a name="todo"></a> Meta-Learning Representations for Continual Learning (NeurIPS2019) [paper] [code]
- <a name="todo"></a> Overcoming Catastrophic Forgetting with Unlabeled Data in the Wild (ICCV2019) [paper]
- <a name="todo"></a> Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation (ICCV2019) [paper]
- <a name="todo"></a> Lifelong GAN: Continual Learning for Conditional Image Generation (ICCV2019) [paper]
- <a name="todo"></a> Continual learning of context-dependent processing in neural networks (Nature Machine Intelligence 2019) [paper] [code]
- <a name="todo"></a> Large Scale Incremental Learning (CVPR2019) [paper] [code]
- <a name="todo"></a> Learning a Unified Classifier Incrementally via Rebalancing (CVPR2019) [paper] [code]
- <a name="todo"></a> Learning Without Memorizing (CVPR2019) [paper]
- <a name="todo"></a> Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning (CVPR2019) [paper]
- <a name="todo"></a> Task-Free Continual Learning (CVPR2019) [paper]
- <a name="todo"></a> Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting (ICML2019) [paper]
- <a name="todo"></a> Efficient Lifelong Learning with A-GEM (ICLR2019) [paper] [code]
- <a name="todo"></a> Learning to Learn without Forgetting By Maximizing Transfer and Minimizing Interference (ICLR2019) [paper] [code]
- <a name="todo"></a> Overcoming Catastrophic Forgetting via Model Adaptation (ICLR2019) [paper]
- <a name="todo"></a> A comprehensive, application-oriented study of catastrophic forgetting in DNNs (ICLR2019) [paper]
2018
- <a name="todo"></a> Memory Replay GANs: learning to generate images from new categories without forgetting (NIPS2018) [paper] [code]
- <a name="todo"></a> Reinforced Continual Learning (NIPS2018) [paper] [code]
- <a name="todo"></a> Online Structured Laplace Approximations for Overcoming Catastrophic Forgetting (NIPS2018) [paper]
- <a name="todo"></a> Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting (R-EWC) (ICPR2018) [paper] [code]
- <a name="todo"></a> Exemplar-Supported Generative Reproduction for Class Incremental Learning (BMVC2018) [paper] [code]
- <a name="todo"></a> End-to-End Incremental Learning (ECCV2018) [paper][code]
- <a name="todo"></a> Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence (ECCV2018)[paper]
- <a name="todo"></a> Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights (ECCV2018) [paper] [code]
- <a name="todo"></a> Memory Aware Synapses: Learning what (not) to forget (ECCV2018) [paper] [code]
- <a name="todo"></a> Lifelong Learning via Progressive Distillation and Retrospection (ECCV2018) [paper]
- <a name="todo"></a> PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning (CVPR2018) [paper] [code]
- <a name="todo"></a> Overcoming Catastrophic Forgetting with Hard Attention to the Task (ICML2018) [paper] [code]
- <a name="todo"></a> Lifelong Learning with Dynamically Expandable Networks (ICLR2018) [paper]
- <a name="todo"></a> FearNet: Brain-Inspired Model for Incremental Learning (ICLR2018) [paper]
2017
- <a name="todo"></a> Incremental Learning of Object Detectors Without Catastrophic Forgetting (ICCV2017) [paper]
- <a name="todo"></a> Overcoming catastrophic forgetting in neural networks (EWC) (PNAS2017) [paper] [code] [code]
- <a name="todo"></a> Continual Learning Through Synaptic Intelligence (ICML2017) [paper] [code]
- <a name="todo"></a> Gradient Episodic Memory for Continual Learning (NIPS2017) [paper] [code]
- <a name="todo"></a> iCaRL: Incremental Classifier and Representation Learning (CVPR2017) [paper] [code]
- <a name="todo"></a> Continual Learning with Deep Generative Replay (NIPS2017) [paper] [code]
- <a name="todo"></a> Overcoming Catastrophic Forgetting by Incremental Moment Matching (NIPS2017) [paper] [code]
- <a name="todo"></a> Expert Gate: Lifelong Learning with a Network of Experts (CVPR2017) [paper]
- <a name="todo"></a> Encoder Based Lifelong Learning (ICCV2017) [paper]