Learning discriminative representations for multi-label image recognition
| dc.contributor.author | Hassanin, M. | |
| dc.contributor.author | Radwan, I. | |
| dc.contributor.author | Khan, S. | |
| dc.contributor.author | Tahtali, M. | |
| dc.date.issued | 2022 | |
| dc.description | Link to a related website: https://unpaywall.org/10.1016/j.jvcir.2022.103448, Open Access via Unpaywall | |
| dc.description.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 well-known 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. | |
| dc.identifier.citation | Journal of Visual Communication and Image Representation, 2022; 83(103448):1-9 | |
| dc.identifier.doi | 10.1016/j.jvcir.2022.103448 | |
| dc.identifier.issn | 1047-3203 | |
| dc.identifier.uri | https://hdl.handle.net/11541.2/29256 | |
| dc.language.iso | en | |
| dc.publisher | Academic Press | |
| dc.rights | Copyright 2022 Elsevier Inc. | |
| dc.source.uri | https://doi.org/10.1016/j.jvcir.2022.103448 | |
| dc.subject | multi-label recognition | |
| dc.subject | multi-label-contrastive learning | |
| dc.subject | contrastive representation | |
| dc.subject | deep learning | |
| dc.title | Learning discriminative representations for multi-label image recognition | |
| dc.type | Journal article | |
| pubs.publication-status | Published | |
| ror.mmsid | 9916640273801831 |