A Task-aware Dual Similarity Network for Fine-grained Few-shot Learning

TL;DR

This paper introduces TDSNet, a dual similarity network that combines global features and local patches with task-aware attention to improve fine-grained few-shot learning performance.

Contribution

The paper proposes a novel TDSNet that integrates global and local features with task-aware attention for enhanced fine-grained few-shot classification.

Findings

TDSNet outperforms existing methods on three fine-grained datasets.

The local feature enhancement improves discriminability of features.

Combining global and local features yields better classification accuracy.

Abstract

The goal of fine-grained few-shot learning is to recognize sub-categories under the same super-category by learning few labeled samples. Most of the recent approaches adopt a single similarity measure, that is, global or local measure alone. However, for fine-grained images with high intra-class variance and low inter-class variance, exploring global invariant features and discriminative local details is quite essential. In this paper, we propose a Task-aware Dual Similarity Network(TDSNet), which applies global features and local patches to achieve better performance. Specifically, a local feature enhancement module is adopted to activate the features with strong discriminability. Besides, task-aware attention exploits the important patches among the entire task. Finally, both the class prototypes obtained by global features and discriminative local patches are employed for prediction. Extensive experiments on three fine-grained datasets demonstrate that the proposed TDSNet achieves competitive performance by comparing with other state-of-the-art algorithms.