English

Class Incremental Learning with Pre-trained Vision-Language Models

Computer Vision and Pattern Recognition 2023-11-01 v1 Machine Learning

Abstract

With the advent of large-scale pre-trained models, interest in adapting and exploiting them for continual learning scenarios has grown. In this paper, we propose an approach to exploiting pre-trained vision-language models (e.g. CLIP) that enables further adaptation instead of only using zero-shot learning of new tasks. We augment a pre-trained CLIP model with additional layers after the Image Encoder or before the Text Encoder. We investigate three different strategies: a Linear Adapter, a Self-attention Adapter, each operating on the image embedding, and Prompt Tuning which instead modifies prompts input to the CLIP text encoder. We also propose a method for parameter retention in the adapter layers that uses a measure of parameter importance to better maintain stability and plasticity during incremental learning. Our experiments demonstrate that the simplest solution -- a single Linear Adapter layer with parameter retention -- produces the best results. Experiments on several conventional benchmarks consistently show a significant margin of improvement over the current state-of-the-art.

Keywords

Cite

@article{arxiv.2310.20348,
  title  = {Class Incremental Learning with Pre-trained Vision-Language Models},
  author = {Xialei Liu and Xusheng Cao and Haori Lu and Jia-wen Xiao and Andrew D. Bagdanov and Ming-Ming Cheng},
  journal= {arXiv preprint arXiv:2310.20348},
  year   = {2023}
}
R2 v1 2026-06-28T13:07:14.468Z