S3C: Self-Supervised Stochastic Classifiers for Few-Shot Class-Incremental Learning

TL;DR

This paper introduces S3C, a self-supervised stochastic classifier designed to improve few-shot class-incremental learning by addressing overfitting and catastrophic forgetting through stochasticity and self-supervision, showing superior results on benchmarks.

Contribution

The paper proposes a novel self-supervised stochastic classifier (S3C) that enhances FSCIL by mitigating overfitting and forgetting, with extensive evaluation demonstrating its effectiveness across various scenarios.

Findings

S3C outperforms state-of-the-art methods on benchmark datasets.

The stochastic classifier reduces overfitting on new classes.

Self-supervision improves generalization to unseen classes.

Abstract

Few-shot class-incremental learning (FSCIL) aims to learn progressively about new classes with very few labeled samples, without forgetting the knowledge of already learnt classes. FSCIL suffers from two major challenges: (i) over-fitting on the new classes due to limited amount of data, (ii) catastrophically forgetting about the old classes due to unavailability of data from these classes in the incremental stages. In this work, we propose a self-supervised stochastic classifier (S3C) to counter both these challenges in FSCIL. The stochasticity of the classifier weights (or class prototypes) not only mitigates the adverse effect of absence of large number of samples of the new classes, but also the absence of samples from previously learnt classes during the incremental steps. This is complemented by the self-supervision component, which helps to learn features from the base classes which generalize well to unseen classes that are encountered in future, thus reducing catastrophic forgetting. Extensive evaluation on three benchmark datasets using multiple evaluation metrics show the effectiveness of the proposed framework. We also experiment on two additional realistic scenarios of FSCIL, namely where the number of annotated data available for each of the new classes can be different, and also where the number of base classes is much lesser, and show that the proposed S3C performs significantly better than the state-of-the-art for all these challenging scenarios.