{
  "id": "2107.11159",
  "version": "v1",
  "published": "2021-07-23T12:10:46.000Z",
  "updated": "2021-07-23T12:10:46.000Z",
  "title": "Learning Discriminative Representations for Multi-Label Image Recognition",
  "authors": [
    "Mohammed Hassanin",
    "Ibrahim Radwan",
    "Salman Khan",
    "Murat Tahtali"
  ],
  "categories": [
    "cs.CV"
  ],
  "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.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2021-07-23T12:10:46.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "multi-label image recognition",
      "learning discriminative representations",
      "discriminative feature",
      "method outperforms state-of-the-art approaches",
      "method first disentangles features corresponding"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}