Spatial Contrastive Learning for Few-Shot Classification

TL;DR

This paper introduces a novel spatial contrastive learning method for few-shot classification that enhances feature transferability and discriminability by using an attention-based objective as an auxiliary regularizer.

Contribution

It proposes a new attention-based spatial contrastive loss that improves the transferability of features in few-shot learning scenarios.

Findings

Outperforms state-of-the-art methods in few-shot classification

Enhances transferability of learned features

Promotes locally discriminative and class-agnostic features

Abstract

In this paper, we explore contrastive learning for few-shot classification, in which we propose to use it as an additional auxiliary training objective acting as a data-dependent regularizer to promote more general and transferable features. In particular, we present a novel attention-based spatial contrastive objective to learn locally discriminative and class-agnostic features. As a result, our approach overcomes some of the limitations of the cross-entropy loss, such as its excessive discrimination towards seen classes, which reduces the transferability of features to unseen classes. With extensive experiments, we show that the proposed method outperforms state-of-the-art approaches, confirming the importance of learning good and transferable embeddings for few-shot learning.