Abstract
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.
Abstract (translated)
少数样本分类增强学习(FSCIL)旨在通过有限的样本获得关于新类别的知识,同时保留基类信息的完整性。现有的方法通过在 novel-class 学习期间冻结特征提取器来解决灾难性遗忘和过拟合问题。然而,这些方法通常会导致基类和新类之间的混淆,即将 novel-class 样本归类为基类。在本文中,我们深入研究了这种现象的原因和解决方案。我们首先解释混淆为特征空间中 novel-class 和基类区域之间的碰撞。然后,我们发现碰撞是由基类特征和像素空间中的标签无关冗余引起的。通过定性和定量实验,我们确定这种冗余是基类训练中的快捷方式,可以解耦以减轻碰撞。根据这种分析,为了解决基类和新类之间的碰撞,我们提出了一个名为 Redundancy Decoupling and Integration(RDI)的 FSCIL 方法。RDI 首先从基类空间中解耦冗余以压缩内基类特征空间。然后,它将冗余作为模拟类来扩展基类特征空间。这一过程有效地压缩了基类特征空间,为 novel 类创建了缓冲区空间,减轻了模型在基类和 novel 类之间的混淆。在包括 CIFAR-100、miniImageNet 和 CUB-200-2011 等基准数据集的广泛实验中,我们的方法证明了其达到了最先进的性能水平。
URL
https://arxiv.org/abs/2405.04918