A multi-strategy contrastive learning framework for weakly supervised semantic segmentation

Yuan, Kunhao, Schaefer, Gerald, Lai, Yu-Kun ORCID: https://orcid.org/0000-0002-2094-5680, Wang, Yifan, Liu, Xiyao, Guan, Lin and Fang, Hui 2023. A multi-strategy contrastive learning framework for weakly supervised semantic segmentation. Pattern Recognition 137 , 109298. 10.1016/j.patcog.2022.109298

Preview

PDF - Published Version Available under License Creative Commons Attribution. Download (5MB) | Preview

Abstract

Weakly supervised semantic segmentation (WSSS) has gained significant popularity as it relies only on weak labels such as image level annotations rather than the pixel level annotations required by supervised semantic segmentation (SSS) methods. Despite drastically reduced annotation costs, typical feature representations learned from WSSS are only representative of some salient parts of objects and less reliable compared to SSS due to the weak guidance during training. In this paper, we propose a novel Multi-Strategy Contrastive Learning (MuSCLe) framework to obtain enhanced feature representations and improve WSSS performance by exploiting similarity and dissimilarity of contrastive sample pairs at image, region, pixel and object boundary levels. Extensive experiments demonstrate the effectiveness of our method and show that MuSCLe outperforms current state-of-the-art methods on the widely used PASCAL VOC 2012 dataset.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	Elsevier
ISSN:	0031-3203
Date of First Compliant Deposit:	14 January 2023
Date of Acceptance:	31 December 2022
Last Modified:	04 May 2023 21:51
URI:	https://orca.cardiff.ac.uk/id/eprint/155872

Actions (repository staff only)

Edit Item