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

By Jaya Kalla, Soma Biswas. 2023

61 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Epidemiology, Meta & Continual Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Epidemiology

In Meta & Continual Learning

Citations in the corpus

A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, methodology): “feature space with virtual prototypes for future classes (Fact [504]), using angular penalty loss with data augmentation (ALICE [329]), using self-supervised learning (S3C [196]),”
A Survey on Few-Shot Class-Incremental Learning (2023, background): “For the first time, Kalla and Biswas (2022) proposed the self-supervised stochastic classifier (S3C) to solve FSCIL.”