Learning to Discover Multi-Class Attentional Regions for Multi-Label Image Recognition

TL;DR

This paper introduces a simple two-stream framework with a multi-class attentional region module for multi-label image recognition, achieving state-of-the-art results efficiently without label dependency.

Contribution

It proposes a novel multi-class attentional region module that reduces the number of regions while maintaining diversity, improving multi-label recognition performance.

Findings

Achieved new state-of-the-art results on three benchmarks.

Effective recognition with low computational cost.

Demonstrated robustness across different settings.

Abstract

Multi-label image recognition is a practical and challenging task compared to single-label image classification. However, previous works may be suboptimal because of a great number of object proposals or complex attentional region generation modules. In this paper, we propose a simple but efficient two-stream framework to recognize multi-category objects from global image to local regions, similar to how human beings perceive objects. To bridge the gap between global and local streams, we propose a multi-class attentional region module which aims to make the number of attentional regions as small as possible and keep the diversity of these regions as high as possible. Our method can efficiently and effectively recognize multi-class objects with an affordable computation cost and a parameter-free region localization module. Over three benchmarks on multi-label image classification, we create new state-of-the-art results with a single model only using image semantics without label dependency. In addition, the effectiveness of the proposed method is extensively demonstrated under different factors such as global pooling strategy, input size and network architecture. Code has been made available at~\url{https://github.com/gaobb/MCAR}.