Official repository for online class incremental learning on stochastic blurry task boundary via mask and visual prompt tuning. Code is based on Si-Blurry and MaPLe. If you use our method or code in your research, please consider citing the paper as follows:
@article{wang2024clip,
title={CLIP model is an Efficient Online Lifelong Learner},
author={Wang, Leyuan and Xiang, Liuyu and Wei, Yujie and Wang, Yunlong and He, Zhaofeng},
journal={arXiv preprint arXiv:2405.15155},
year={2024}
}
- Pytorch
- timm
or you can install a conda environment with :
conda env create -f environment.yml
bash scripts/lora_clip.sh