English

Learning Discriminative Representations for Multi-Label Image Recognition

Computer Vision and Pattern Recognition 2021-07-26 v1

Abstract

Multi-label recognition is a fundamental, and yet is a challenging task in computer vision. Recently, deep learning models have achieved great progress towards learning discriminative features from input images. However, conventional approaches are unable to model the inter-class discrepancies among features in multi-label images, since they are designed to work for image-level feature discrimination. In this paper, we propose a unified deep network to learn discriminative features for the multi-label task. Given a multi-label image, the proposed method first disentangles features corresponding to different classes. Then, it discriminates between these classes via increasing the inter-class distance while decreasing the intra-class differences in the output space. By regularizing the whole network with the proposed loss, the performance of applying the wellknown ResNet-101 is improved significantly. Extensive experiments have been performed on COCO-2014, VOC2007 and VOC2012 datasets, which demonstrate that the proposed method outperforms state-of-the-art approaches by a significant margin of 3:5% on large-scale COCO dataset. Moreover, analysis of the discriminative feature learning approach shows that it can be plugged into various types of multi-label methods as a general module.

Keywords

Cite

@article{arxiv.2107.11159,
  title  = {Learning Discriminative Representations for Multi-Label Image Recognition},
  author = {Mohammed Hassanin and Ibrahim Radwan and Salman Khan and Murat Tahtali},
  journal= {arXiv preprint arXiv:2107.11159},
  year   = {2021}
}
R2 v1 2026-06-24T04:27:33.618Z