Sparse Spatial Transformers for Few-Shot Learning

TL;DR

This paper introduces SSFormers, a transformer-based approach that enhances few-shot learning by identifying task-relevant image patches through sparse spatial transformers, improving classification accuracy with limited data.

Contribution

The paper proposes a novel sparse spatial transformer architecture that selectively emphasizes relevant image patches, effectively capturing contextual information for few-shot learning.

Findings

Outperforms state-of-the-art few-shot learning methods on benchmark datasets.

Effectively identifies task-relevant features using sparse spatial transformers.

Demonstrates improved generalization with limited training data.

Abstract

Learning from limited data is challenging because data scarcity leads to a poor generalization of the trained model. A classical global pooled representation will probably lose useful local information. Many few-shot learning methods have recently addressed this challenge using deep descriptors and learning a pixel-level metric. However, using deep descriptors as feature representations may lose image contextual information. Moreover, most of these methods independently address each class in the support set, which cannot sufficiently use discriminative information and task-specific embeddings. In this paper, we propose a novel transformer-based neural network architecture called sparse spatial transformers (SSFormers), which finds task-relevant features and suppresses task-irrelevant features. Particularly, we first divide each input image into several image patches of different sizes to obtain dense local features. These features retain contextual information while expressing local information. Then, a sparse spatial transformer layer is proposed to find spatial correspondence between the query image and the full support set to select task-relevant image patches and suppress task-irrelevant image patches. Finally, we propose using an image patch-matching module to calculate the distance between dense local representations, thus determining which category the query image belongs to in the support set. Extensive experiments on popular few-shot learning benchmarks demonstrate the superiority of our method over state-of-the-art methods. Our source code is available at \url{https://github.com/chenhaoxing/ssformers}.