跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.24445 · v1

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

首次提交 2026-11-18 21:56
版本更新 2026-11-18 21:56
雷达观测 2026-11-19 15:04
arXiv ↗PDF ↗

摘要

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.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-18 21:56 · 最新观测版本

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

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.

查看此版本解读 →查看此版本原文 ↗