Class-incremental learning (CIL) has been widely studied under the setting of starting from a small number of classes (base classes). Instead, we explore an understudied real-world setting of CIL that starts with a strong model pre-trained on a large number of base classes. We hypothesize that a strong base model can provide a good representation for novel classes and incremental learning can be done with small adaptations. We propose a 2-stage training scheme, i) feature augmentation -- cloning part of the backbone and fine-tuning it on the novel data, and ii) fusion -- combining the base and novel classifiers into a unified classifier. Experiments show that the proposed method significantly outperforms state-of-the-art CIL methods on the large-scale ImageNet dataset (e.g. +10% overall accuracy than the best). We also propose and analyze understudied practical CIL scenarios, such as base-novel overlap with distribution shift. Our proposed method is robust and generalizes to all analyzed CIL settings. Code is available at https://github.com/amazon-research/sp-cil.
@article{arxiv.2204.03634,
title = {Class-Incremental Learning with Strong Pre-trained Models},
author = {Tz-Ying Wu and Gurumurthy Swaminathan and Zhizhong Li and Avinash Ravichandran and Nuno Vasconcelos and Rahul Bhotika and Stefano Soatto},
journal= {arXiv preprint arXiv:2204.03634},
year = {2022}
}
Comments
Accepted at CVPR 2022, code is available at https://github.com/amazon-research/sp-cil