Few-shot class-incremental learning (FSCIL) aims to build machine learning
model that can continually learn new concepts from a few data samples, without
forgetting knowledge of old classes.
The challenges of FSCIL lies in the limited data of new classes, which not
only lead to significant overfitting issues but also exacerbates the notorious
catastrophic forgetting problems. As proved in early studies, building sample
relationships is beneficial for learning from few-shot samples. In this paper,
we promote the idea to the incremental scenario, and propose a Sample-to-Class
(S2C) graph learning method for FSCIL.
Specifically, we propose a Sample-level Graph Network (SGN) that focuses on
analyzing sample relationships within a single session. This network helps
aggregate similar samples, ultimately leading to the extraction of more refined
class-level features.
Then, we present a Class-level Graph Network (CGN) that establishes
connections across class-level features of both new and old classes. This
network plays a crucial role in linking the knowledge between different
sessions and helps improve overall learning in the FSCIL scenario. Moreover, we
design a multi-stage strategy for training S2C model, which mitigates the
training challenges posed by limited data in the incremental process.
The multi-stage training strategy is designed to build S2C graph from base to
few-shot stages, and improve the capacity via an extra pseudo-incremental
stage. Experiments on three popular benchmark datasets show that our method
clearly outperforms the baselines and sets new state-of-the-art results in
FSCIL.

基于样本到类的图学习方法（Sample-to-Class，S2C）的小样本增量学习（Few-shot class-incremental learning，FSCIL）对于从少量数据样本中学习新概念且不忘记旧类别的知识具有重要意义。本文提出了样本级图网络（Sample-level Graph Network，SGN）和类别级图网络（Class-level Graph Network，CGN）来分析样本之间的关系，并通过多阶段的训练策略来提高模型的学习能力。实验证明，该方法在 FSCIL 中明显优于基线模型，取得了新的最先进结果。