Multi-class part parsing based on multi-class boundaries

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 2025. Multi-class part parsing based on multi-class boundaries. Presented at: IEEE International Conference on Image Processing, Anchorage, AK, USA, 14-17 September 2025. 2025 IEEE International Conference on Image Processing (ICIP). IEEE, pp. 2498-2503. 10.1109/icip55913.2025.11084502

Full text not available from this repository.

Abstract

Multi-class part parsing is a dense prediction task that segments objects into semantic components with multi-level abstractions. Despite its significance, this task remains challenging due to ambiguities at both part and class levels. In this paper, we propose a network that incorporates multi-class boundaries to precisely identify and emphasize the spatial boundaries of part classes, thereby improving segmentation quality. Additionally, we employ a weighted multi-label cross-entropy loss function to ensure balanced and effective learning from all parts. Experimental results validate the effectiveness of the proposed method, demonstrating its ability to enhance baseline performance on benchmark datasets.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Status:	Published
Schools:	Schools > Engineering Schools > Computer Science & Informatics
Publisher:	IEEE
ISBN:	9798331523800
ISSN:	1522-4880
Last Modified:	02 Sep 2025 11:01
URI:	https://orca.cardiff.ac.uk/id/eprint/180830

Actions (repository staff only)

Edit Item