Prompt-Based Exemplar Super-Compression and Regeneration for Class-Incremental Learning


Ruxiao Duan (Yale University), Jieneng Chen (Johns Hopkins University), Adam Kortylewski (University of Freiburg), Alan Yuille (Johns Hopkins University), Yaoyao Liu (University of Illinois Urbana-Champaign)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)Supplementary

Abstract

Replay-based methods in class-incremental learning (CIL) have attained remarkable success. Despite their effectiveness, the inherent memory restriction results in saving a limited number of exemplars with poor diversity. In this paper, we introduce PESCR, a novel approach that substantially increases the quantity and enhances the diversity of exemplars based on a pre-trained general-purpose diffusion model, without fine-tuning it on target datasets or storing it in the memory buffer. Images are compressed into visual and textual prompts, which are saved instead of the original images, decreasing memory consumption by a factor of 24. In subsequent phases, diverse exemplars are regenerated by the diffusion model. We further propose partial compression and diffusion-based data augmentation to minimize the domain gap between generated exemplars and real images. PESCR significantly improves CIL performance across multiple benchmarks, e.g., 3.2% above the previous state-of-the-art on ImageNet-100. The code is available at https://github.com/KerryDRX/PESCR.

Citation

@inproceedings{Duan_2025_BMVC,
author    = {Ruxiao Duan and Jieneng Chen and Adam Kortylewski and Alan Yuille and Yaoyao Liu},
title     = {Prompt-Based Exemplar Super-Compression and Regeneration for Class-Incremental Learning},
booktitle = {36th British Machine Vision Conference 2025, {BMVC} 2025, Sheffield, UK, November 24-27, 2025},
publisher = {BMVA},
year      = {2025},
url       = {https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_113/paper.pdf}
}


Copyright © 2025 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection