基于角度-范数联合分类器的少样本类增量学习嵌入空间分配
Embedding Space Allocation with Angle-Norm Joint Classifiers for Few-Shot Class-Incremental Learning
AI总结：
针对少样本类增量学习中特征空间占用和样本不足问题，提出SAAN框架，通过类中心引导划分子空间并利用范数差异生成角度-范数联合logits，实现SOTA性能并可作为插件增强其他方法。
摘要：
少样本类增量学习（FSCIL）旨在仅从少量样本中持续学习新类而不遗忘旧类，要求智能体适应动态环境。FSCIL结合了类增量学习和少样本学习的特征与挑战：(i)当前类占据整个特征空间，不利于学习新类。(ii)增量轮次中样本数量少，不足以充分训练。在现有的主流虚拟类方法中，针对挑战(i)，它们尝试使用虚拟类作为占位符。然而，新类未必与虚拟类对齐。对于挑战(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。为解决先前方法中的这些问题，我们提出了类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，为所有类提供平衡空间，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将特征空间划分为多个子空间，并通过预设类别中心引导样本，为每个会话分配专用子空间。针对挑战(ii)，SAAN为每个类建立范数分布并生成角度-范数联合logits。实验表明，SAAN能实现最先进的性能，并可作为插件直接嵌入其他SOTA方法，进一步提升其性能。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
