Few-shot class-incremental learning (FSCIL) aims to continually learn new classes from only a few samples without forgetting previous ones, requiring intelligent agents to adapt to dynamic environments. FSCIL combines the characteristics and challenges of class-incremental learning and few-shot learning: (i) Current classes occupy the entire feature space, which is detrimental to learning new classes. (ii) The small number of samples in incremental rounds is insufficient for fully training. In existing mainstream virtual class methods, for addressing the challenge (i), they attempt to use virtual classes as placeholders. However, new classes may not necessarily align with the virtual classes. For the challenge (ii), they replace trainable fully connected layers with Nearest Class Mean (NCM) classifiers based on cosine similarity, but NCM classifiers do not account for sample imbalance issues. To address these issues in previous methods, we propose the class-center guided embedding Space Allocation with Angle-Norm joint classifiers (SAAN) learning framework, which provides balanced space for all classes and leverages norm differences caused by sample imbalance to enhance classification criteria. Specifically, for challenge (i), SAAN divides the feature space into multiple subspaces and allocates a dedicated subspace for each session by guiding samples with the pre-set category centers. For challenge (ii), SAAN establishes a norm distribution for each class and generates angle-norm joint logits. Experiments demonstrate that SAAN can achieve state-of-the-art performance and it can be directly embedded into other SOTA methods as a plug-in, further enhancing their performance.

翻译：小样本类增量学习（FSCIL）旨在仅用少量样本持续学习新类别而不遗忘先前类别，要求智能体适应动态环境。FSCIL结合了类增量学习与小样本学习的特性与挑战：（i）当前类别占据整个特征空间，不利于新类别的学习。（ii）增量轮次中样本数量过少，不足以充分训练。现有主流虚拟类方法中，针对挑战（i），它们尝试使用虚拟类作为占位符，但新类别未必与虚拟类对齐；针对挑战（ii），它们用基于余弦相似度的最近类均值（NCM）分类器替代可训练的全连接层，但NCM分类器未考虑样本不平衡问题。为改进现有方法的不足，本文提出基于类别中心引导的嵌入空间分配与角度-范数联合分类器（SAAN）学习框架，该框架为所有类别提供均衡空间，并利用样本不平衡引起的范数差异增强分类准则。具体而言，针对挑战（i），SAAN通过预设类别中心引导样本，将特征空间划分为多个子空间并为每个会话分配专属子空间；针对挑战（ii），SAAN为每个类别建立范数分布并生成角度-范数联合逻辑值。实验表明SAAN能取得最先进的性能，并可作为插件直接嵌入其他SOTA方法以进一步提升其性能。