Few-shot class-incremental learning (FSCIL) aims to acquire knowledge from novel classes with limited samples while retaining information about base classes. Existing methods address catastrophic forgetting and overfitting by freezing the feature extractor during novel-class learning. However, these methods usually tend to cause the confusion between base and novel classes, i.e., classifying novel-class samples into base classes. In this paper, we delve into this phenomenon to study its cause and solution. We first interpret the confusion as the collision between the novel-class and the base-class region in the feature space. Then, we find the collision is caused by the label-irrelevant redundancies within the base-class feature and pixel space. Through qualitative and quantitative experiments, we identify this redundancy as the shortcut in the base-class training, which can be decoupled to alleviate the collision. Based on this analysis, to alleviate the collision between base and novel classes, we propose a method for FSCIL named Redundancy Decoupling and Integration (RDI). RDI first decouples redundancies from base-class space to shrink the intra-base-class feature space. Then, it integrates the redundancies as a dummy class to enlarge the inter-base-class feature space. This process effectively compresses the base-class feature space, creating buffer space for novel classes and alleviating the model's confusion between the base and novel classes. Extensive experiments across benchmark datasets, including CIFAR-100, miniImageNet, and CUB-200-2011 demonstrate that our method achieves state-of-the-art performance.

翻译：小样本类增量学习（FSCIL）旨在从样本量有限的 novel classes 中获取知识，同时保留关于 base classes 的信息。现有方法通过在 novel classes 学习阶段冻结特征提取器来应对灾难性遗忘和过拟合问题。然而，这些方法往往会导致 base classes 与 novel classes 之间的混淆，即将 novel classes 样本误分类到 base classes 中。本文深入探究这一现象，以研究其成因与解决方案。我们首先将该混淆解释为特征空间中 novel class 区域与 base class 区域之间的冲突。接着，我们发现该冲突是由 base class 特征空间与像素空间中与标签无关的冗余信息引起的。通过定性与定量实验，我们识别出该冗余信息是 base class 训练中的捷径，解耦该冗余信息可缓解冲突。基于此分析，为缓解 base classes 与 novel classes 之间的冲突，我们提出了一种名为冗余解耦与集成（RDI）的 FSCIL 方法。RDI 首先从 base class 空间中解耦冗余信息以收缩 base class 内部的特征空间，随后将这些冗余信息集成为一个虚拟类以扩大 base class 间的特征空间。这一过程有效压缩了 base class 特征空间，为 novel classes 创造了缓冲空间，从而缓解了模型在 base classes 与 novel classes 之间的混淆。在 CIFAR-100、miniImageNet 和 CUB-200-2011 等基准数据集上的大量实验表明，我们的方法达到了最先进的性能。