发表机构
School of Computer Science and Technology, Huazhong University of Science and Technology（华中科技大学计算机科学与技术学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究少样本类别增量学习中误分类问题，提出基于组合学习的方法，通过学习公共和判别原语集缓解区域捷径，经实验验证该方法在准确性和可解释性上优于现有方法。
AI 中文摘要
少样本类别增量学习（FSCIL）旨在仅用少量样本增量学习新类别，同时避免遗忘基础类别。然而，当前方法存在将新类别样本误分类为基础类别的倾向，这是由于对新类别样本上基础类别判别区域过度关注所致。本文旨在探索其潜在机制以进行解释和解决。首先提供一种组合视角来分析新类别样本上转移和重用的空间模式。通过大量实验和理论分析，从经验和理论上确定模型基础类别训练中存在一种捷径，即过度关注最具判别力的区域（原语），称为区域捷径。最后基于此解释，提出一种基于组合学习的方法来学习两个原语集（一个公共集和一个判别集），通过约束模型学习和利用公共原语集进行基础和新类别识别来缓解区域捷径。在标准FSCIL基准上的大量实验证明了该方法的有效性，在准确性和可解释性方面均比现有最先进方法有持续改进。
英文摘要
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.
CommentsAccepted by TMM 2026
