🎉The code repository for "Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning" [paper](CVPR24) in PyTorch. If you use any content of this repo for your work, please cite the following bib entry:
@inproceedings{zhou2024expandable,
title={Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning},
author={Zhou, Da-Wei and Sun, Hai-Long and Ye, Han-Jia and Zhan, De-Chuan},
booktitle={CVPR},
pages={23554--23564},
year={2024}
}
Class-Incremental Learning (CIL) requires a learning system to continually learn new classes without forgetting. Despite the strong performance of Pre-Trained Models (PTMs) in CIL, a critical issue persists: learning new classes often results in the overwriting of old ones. Excessive modification of the network causes forgetting, while minimal adjustments lead to an inadequate fit for new classes. As a result, it is desired to figure out a way of efficient model updating without harming former knowledge.
In this paper, we propose ExpAndable Subspace Ensemble (EASE) for PTM-based CIL. To enable model updating without conflict, we train a distinct lightweight adapter module for each new task, aiming to create task-specific subspaces. These adapters span a high-dimensional feature space, enabling joint decision-making across multiple subspaces. As data evolves, the expanding subspaces render the old class classifiers incompatible with new-stage spaces. Correspondingly, we design a semantic-guided prototype complement strategy that synthesizes old classes’ new features without using any old class instance. Extensive experiments on seven benchmark datasets verify EASE’s state-of-the-art performance.
We conducted experiments on seven benchmark datasets to verify the competitive performance of EASE.
We provide the processed datasets as follows:
- CIFAR100: will be automatically downloaded by the code.
- 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
- ObjectNet: Onedrive: link You can also refer to the filelist if the file is too large to download.
You need to modify the path of the datasets in ./utils/data.py according to your own path.
These datasets are referenced in the ADAM
Please follow the settings in the exps folder to prepare json files, and then run:
python main.py --config ./exps/[filename].json
Here is an example of how to run the code
if you want to run the cifar dataset using ViT-B/16-IN1K, you can follow the script:
python main.py --config ./exps/ease_cifar.json
if you want to run the cifar dataset using ViT-B/16-IN21K, you can follow the script:
python main.py --config ./exps/ease_cifar_in21k.json
After running the code, you will get a log file in the logs/ease/cifar224/ folder.
We would like to express our gratitude to the following repositories for offering valuable components and functions that contributed to our work.
