Afpsnet: multi-class part parsing based on scaled attention and feature fusion

Alsudays, Njuod, Wu, Jing ORCID: https://orcid.org/0000-0001-5123-9861, Lai, Yukun ORCID: https://orcid.org/0000-0002-2094-5680 and Ji, Ze ORCID: https://orcid.org/0000-0002-8968-9902 2023. Afpsnet: multi-class part parsing based on scaled attention and feature fusion. Presented at: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, Hawaii,, 3-7 Jan 2023. 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). IEEE, pp. 4022-4031. 10.1109/WACV56688.2023.00402

Preview

PDF - Accepted Post-Print Version Available under License Creative Commons Attribution. Download (25MB) | Preview

Abstract

Multi-class part parsing is a dense prediction task that seeks to simultaneously detect multiple objects and the semantic parts within these objects in the scene. This problem is important in providing detailed object understanding, but is challenging due to the existence of both class-level and part-level ambiguities. In this paper, we propose to integrate an attention refinement module and a feature fusion module to tackle the part-level ambiguity. The attention refinement module aims to enhance the feature representations by focusing on important features. The feature fusion module aims to improve the fusion operation for different scales of features. We also propose an object-to-part training strategy to tackle the class-level ambiguity, which improves the localization of parts by exploiting prior knowledge of objects. The experimental results demonstrated the effectiveness of the proposed modules and the training strategy, and showed that our proposed method achieved state-of-the-art performance on the benchmark datasets

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Status:	In Press
Schools:	Advanced Research Computing @ Cardiff (ARCCA) Computer Science & Informatics
Publisher:	IEEE
ISBN:	9781665493475
ISSN:	2642-9381
Date of First Compliant Deposit:	13 January 2023
Date of Acceptance:	11 October 2022
Last Modified:	14 Jun 2024 15:14
URI:	https://orca.cardiff.ac.uk/id/eprint/155844

Actions (repository staff only)

Edit Item