SyncAI.news, a Varaisys broadcasting
Retroactive Concept Bottleneck Models for Exemplar-Free Class-Incremental Learning
YJ

Yang Ji, Ying Sun, Yuanxin Zhuang, Yuting Zhang

· 1 min read

ResearcharXiv cs.CV

Retroactive Concept Bottleneck Models for Exemplar-Free Class-Incremental Learning

arXiv:2611.24445v1 Announce Type: new Abstract: Exemplar-free class-incremental learning (EFCIL) requires models to learn new classes sequentially without retaining training samples from previous tasks. Continual concept bottleneck models (CBMs) make their predictions interpretable by identifying visual concepts in an image and using them to score each class. However, these methods typically focus on preserving learned concepts or approximating past classes with generated features, which can leave new concepts underused in old-class predictions. We propose RetroCBM, which retains a small set of vocabulary-independent statistics relating frozen visual features to the embedding space of a pretrained vision-language model. Even after earlier training images have been discarded, we can use these statistics to supervise new concepts. To do so, we develop a retroactive regression rule that yields the same predictor for each new concept as class-balanced ridge regression on all images seen so far. We then reproject the stored statistics to recover the full-history squared classification loss and thus learn how much each new concept should contribute to old-class predictions. Since the classifier may use systematic concept errors to distinguish nearby classes, we further introduce a graph-weighted penalty on the margin shifts caused by those errors. Across six datasets, RetroCBM outperforms state-of-the-art interpretable methods in all class-incremental settings, with an 18.1\% relative gain in mean average incremental accuracy over the strongest exemplar-free baseline.

Original source

This story was published by arXiv cs.CV and written by Yang Ji, Ying Sun, Yuanxin Zhuang, Yuting Zhang. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News