A Simple Task-aware Contrastive Local Descriptor Selection Strategy for Few-shot Learning between inter class and intra class

TL;DR

This paper introduces TCDSNet, a task-aware contrastive local descriptor selection method that improves few-shot image classification by adaptively selecting discriminative local descriptors, outperforming existing approaches on various datasets.

Contribution

The paper proposes a novel task-aware contrastive local descriptor selection network that adaptively filters local descriptors based on task-specific discriminative scores, enhancing few-shot learning performance.

Findings

Outperforms state-of-the-art methods on general datasets.

Effective in both general and fine-grained classification tasks.

Demonstrates the importance of task-aware descriptor selection.

Abstract

Few-shot image classification aims to classify novel classes with few labeled samples. Recent research indicates that deep local descriptors have better representational capabilities. These studies recognize the impact of background noise on classification performance. They typically filter query descriptors using all local descriptors in the support classes or engage in bidirectional selection between local descriptors in support and query sets. However, they ignore the fact that background features may be useful for the classification performance of specific tasks. This paper proposes a novel task-aware contrastive local descriptor selection network (TCDSNet). First, we calculate the contrastive discriminative score for each local descriptor in the support class, and select discriminative local descriptors to form a support descriptor subset. Finally, we leverage support descriptor subsets to adaptively select discriminative query descriptors for specific tasks. Extensive experiments demonstrate that our method outperforms state-of-the-art methods on both general and fine-grained datasets.