A multi-strategy contrastive learning framework for weakly supervised semantic segmentation. (May 2023)

• Record Type: Journal Article
• Authors: Yuan, Kunhao; Schaefer, Gerald; Lai, Yu-Kun; Wang, Yifan; Liu, Xiyao; Guan, Lin; Fang, Hui
• Is Part Of: Pattern recognition. Volume 137(2023)
• Publication Date: 2023-05
• Subjects: Weakly supervised learning -- Representation learning -- Contrastive learning -- Semantic segmentation; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2022.109298
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: Multi-contrast learning framework for WSSS with only image-level labels. Novel Boundary Enhancement viA Contrastive Orientation Navigation (BEACON). SOTA result on PASCAL VOC 2012 benchmark. 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.