Strategic Base Representation Learning via Feature Augmentations for Few-Shot Class Incremental Learning

TL;DR

This paper introduces a feature augmentation contrastive learning framework for few-shot class incremental learning, improving class separation and performance on benchmark datasets by expanding feature space and using self-supervised contrastive loss.

Contribution

The paper proposes a novel feature augmentation contrastive learning method that enhances class separation and integrates new classes effectively in FSCIL.

Findings

Outperforms existing methods on CIFAR100, miniImageNet, and CUB200 datasets.

Achieves state-of-the-art results in few-shot class incremental learning.

Effectively expands feature space for better class separation.

Abstract

Few-shot class incremental learning implies the model to learn new classes while retaining knowledge of previously learned classes with a small number of training instances. Existing frameworks typically freeze the parameters of the previously learned classes during the incorporation of new classes. However, this approach often results in suboptimal class separation of previously learned classes, leading to overlap between old and new classes. Consequently, the performance of old classes degrades on new classes. To address these challenges, we propose a novel feature augmentation driven contrastive learning framework designed to enhance the separation of previously learned classes to accommodate new classes. Our approach involves augmenting feature vectors and assigning proxy labels to these vectors. This strategy expands the feature space, ensuring seamless integration of new classes within the expanded space. Additionally, we employ a self-supervised contrastive loss to improve the separation between previous classes. We validate our framework through experiments on three FSCIL benchmark datasets: CIFAR100, miniImageNet, and CUB200. The results demonstrate that our Feature Augmentation driven Contrastive Learning framework significantly outperforms other approaches, achieving state-of-the-art performance.