Home

Awesome

DVC

Code For CVPR2022 paper "Not Just Selection, but Exploration: Online Class-Incremental Continual Learning via Dual View Consistency"

Usage

Requirements

requirements.txt

Data preparation

CIFAR-100

  python general_main.py --data  cifar100 --cl_type nc --agent ER_DVC  --retrieve MGI --update random --mem_size 1000 --dl_weight 4.0

CIFAR-10

  python general_main.py --data cifar10 --cl_type nc --agent ER_DVC --retrieve MGI --update random --mem_size 200 --dl_weight 2.0  --num_tasks 5

Mini-Imagenet

python general_main.py --data  mini_imagenet --cl_type nc --agent ER_DVC  --retrieve MGI --update random --mem_size 1000 --dl_weight 4.0

Reference

online-continual-learning

agmax

If our code or models help your work, please cite our paper:

@InProceedings{Gu_2022_CVPR,
    author    = {Gu, Yanan and Yang, Xu and Wei, Kun and Deng, Cheng},
    title     = {Not Just Selection, but Exploration: Online Class-Incremental Continual Learning via Dual View Consistency},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2022},
    pages     = {7442-7451}
}