Shaping Visual Representations with Attributes for Few-Shot Recognition

TL;DR

This paper introduces a novel attribute-shaped learning framework for few-shot recognition that jointly predicts query attributes and learns discriminative visual features, improving performance by leveraging semantic attribute information for both support and query sets.

Contribution

The proposed attribute-shaped learning (ASL) framework uniquely predicts query attributes and integrates them into visual feature learning, enhancing few-shot recognition performance.

Findings

Achieves competitive results on CUB and SUN benchmarks.

Introduces a visual-attribute predictor for query attribute prediction.

Designs an attribute-visual attention module for improved feature discrimination.

Abstract

Few-shot recognition aims to recognize novel categories under low-data regimes. Some recent few-shot recognition methods introduce auxiliary semantic modality, i.e., category attribute information, into representation learning, which enhances the feature discrimination and improves the recognition performance. Most of these existing methods only consider the attribute information of support set while ignoring the query set, resulting in a potential loss of performance. In this letter, we propose a novel attribute-shaped learning (ASL) framework, which can jointly perform query attributes generation and discriminative visual representation learning for few-shot recognition. Specifically, a visual-attribute predictor (VAP) is constructed to predict the attributes of queries. By leveraging the attributes information, an attribute-visual attention module (AVAM) is designed, which can adaptively utilize attributes and visual representations to learn more discriminative features. Under the guidance of attribute modality, our method can learn enhanced semantic-aware representation for classification. Experiments demonstrate that our method can achieve competitive results on CUB and SUN benchmarks. Our source code is available at: \url{https://github.com/chenhaoxing/ASL}.