Multi-Pretext Attention Network for Few-shot Learning with Self-supervision

TL;DR

This paper introduces a novel self-supervised learning approach for few-shot learning that leverages endogenous correlations among samples through a graph-driven clustering method and an attention-based network to enhance feature universality.

Contribution

It proposes a new augmentation-free self-supervised method and an attention mechanism to effectively combine multiple learning strategies for improved few-shot learning.

Findings

Outperforms state-of-the-art methods on miniImageNet.

Effectively utilizes endogenous correlations among samples.

Enhances feature generalization for few-shot tasks.

Abstract

Few-shot learning is an interesting and challenging study, which enables machines to learn from few samples like humans. Existing studies rarely exploit auxiliary information from large amount of unlabeled data. Self-supervised learning is emerged as an efficient method to utilize unlabeled data. Existing self-supervised learning methods always rely on the combination of geometric transformations for the single sample by augmentation, while seriously neglect the endogenous correlation information among different samples that is the same important for the task. In this work, we propose a Graph-driven Clustering (GC), a novel augmentation-free method for self-supervised learning, which does not rely on any auxiliary sample and utilizes the endogenous correlation information among input samples. Besides, we propose Multi-pretext Attention Network (MAN), which exploits a specific attention mechanism to combine the traditional augmentation-relied methods and our GC, adaptively learning their optimized weights to improve the performance and enabling the feature extractor to obtain more universal representations. We evaluate our MAN extensively on miniImageNet and tieredImageNet datasets and the results demonstrate that the proposed method outperforms the state-of-the-art (SOTA) relevant methods.