Alleviating Regional Shortcuts for Few-Shot Class-Incremental Learning
This work addresses the critical problem of catastrophic forgetting and novel-class misclassification in FSCIL, which is important for continual learning in resource-constrained scenarios.
The paper identifies a regional shortcut in few-shot class-incremental learning (FSCIL) where models over-focus on base-class-discriminative regions, causing misclassification of novel classes into base classes. They propose a compositional-learning method that learns common and discriminative primitive sets, achieving consistent improvements over state-of-the-art methods on standard benchmarks.
Few-shot class-incremental learning (FSCIL) aims to incrementally learn novel classes with only a few samples while avoiding forgetting base classes. However, current methods show a tendency to misclassify novel-class samples into base classes, which we find to be caused by the excessive focus on base-class-discriminative regions on novel-class samples. In this work, we aim to explore the underlying mechanism for an interpretation and solution. We first provide a compositional view to analyze the transferred and reused spatial patterns on novel-class samples. Then, through extensive experiments and theoretical analysis, we identify both empirically and theoretically that a shortcut exists in the model's base-class training, which naturally forms the excessive focus on only the most discriminative regions (primitives), which we term as the regional shortcut. Finally, based on this interpretation, to address this problem, we propose a compositional-learning-based method to learn two primitive sets (a common set and a discriminative set), which alleviates the regional shortcut by constraining the model to learn and utilize the common primitive set for base- and novel-class recognition. Extensive experiments on standard FSCIL benchmarks demonstrate the effectiveness of our approach, yielding consistent improvements over existing state-of-the-art methods in both accuracy and interpretability.