Home

Awesome

Awesome-Mix

This repository contains a list of papers on the A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability, and we categorize them based on our proposed taxonomy.

We will try to make this list updated. If you found any error or any missed paper, please don't hesitate to open issues or pull requests.

A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability
Chengtai Cao, Fan Zhou, Yurou Dai, and Jianping Wang
arXiv:2212.10888

Methodology

Mixup-based

Mixup

Mixng in Embedding Space

Adaptive Mix Strategy

Sample Selection

Saliency & Style For Guidance

Diversity in Mixup

Miscellaneous Mixup Methods

Cutmix-based

Cutmix

Integration with Saliency Information

Improved Divergence

Border Smooth

Other Cutmix Techniques

Beyond Mixup & Cutmix

Mixing with itself

Incorporating multiple MixDA approaches

Integrating with other DA methods

MixDA Applications

Semi-Supervised Learning

Contrastive Learning

Metric Learning

  1. [Embedding Expansion -- CVPR 2020] Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learning(2020) [code]
  2. [Metrix -- ICLR 2022] It Takes Two to Tango: Mixup for Deep Metric Learning(2022) [code]

Adversarial Training

Generative Models

Domain Adaption

Natural Language Processing

Graph Neural Networks

Federated Learning

Other Applications

Point Clound

Multiple-modal Learning

Explainability Analysis of MixDA

Vicinal Risk Minimization

Model Regularization

Uncertainty & Calibration

License

This project is released under the Apache 2.0 license.

Related Project