Class-Specific Channel Attention for Few-Shot Learning

TL;DR

This paper introduces Class-Specific Channel Attention (CSCA), a novel module that enhances feature discrimination in few-shot learning by focusing on class-specific channels, leading to state-of-the-art results across multiple benchmarks.

Contribution

The paper proposes the CSCA module that learns class-specific channel weights to improve feature representation in few-shot learning, addressing task distribution shifts.

Findings

Achieves new state-of-the-art results on standard FSL benchmarks.

Effectively highlights discriminative channels for each class.

Performs well in both inductive and cross-domain settings.

Abstract

Few-Shot Learning (FSL) has attracted growing attention in computer vision due to its capability in model training without the need for excessive data. FSL is challenging because the training and testing categories (the base vs. novel sets) can be largely diversified. Conventional transfer-based solutions that aim to transfer knowledge learned from large labeled training sets to target testing sets are limited, as critical adverse impacts of the shift in task distribution are not adequately addressed. In this paper, we extend the solution of transfer-based methods by incorporating the concept of metric-learning and channel attention. To better exploit the feature representations extracted by the feature backbone, we propose Class-Specific Channel Attention (CSCA) module, which learns to highlight the discriminative channels in each class by assigning each class one CSCA weight vector. Unlike general attention modules designed to learn global-class features, the CSCA module aims to learn local and class-specific features with very effective computation. We evaluated the performance of the CSCA module on standard benchmarks including miniImagenet, Tiered-ImageNet, CIFAR-FS, and CUB-200-2011. Experiments are performed in inductive and in/cross-domain settings. We achieve new state-of-the-art results.