Local Classfier Alignment

Environment

This repository is tested in an Anaconda environment. To reproduce exactly, create your environment as follows:

conda create -y -n continual_learning python=3.9
conda activate continual_learning
pip install -r requirements.tx

To change the location of download dataset, update the variable DATA_ROOT inside utils/data.py

To reproduce results run code of the form

python lca.py

Datasets

Five of the datasets tested on are specific splits and/or subsets of the full original datasets. These versions were created by Zhou et al in:

@article{zhou2023revisiting,
    author = {Zhou, Da-Wei and Ye, Han-Jia and Zhan, De-Chuan and Liu, Ziwei},
    title = {Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need},
    journal = {arXiv preprint arXiv:2303.07338},
    year = {2023}
}

• The following links are copied verbatim from the README.md file in the github repository of Zhou et al at https://github.com/zhoudw-zdw/RevisitingCIL:

CUB200: Google Drive: link or Onedrive: link
ImageNet-R: Google Drive: link or Onedrive: link
ImageNet-A:Google Drive: link or Onedrive: link
OmniBenchmark: Google Drive: link or Onedrive: link
VTAB: Google Drive: link or Onedrive: link

Acknowledgment

This repo is based on aspects of https://github.com/LAMDA-CL/LAMDA-PILOT