Weakly-supervised Semantic Segmentation via Dual-stream Contrastive Learning of Cross-image Contextual Information
This work addresses the problem of improving segmentation accuracy with limited supervision for computer vision applications, representing an incremental advance by integrating cross-image information into existing WSSS methods.
The paper tackles the performance gap in weakly supervised semantic segmentation (WSSS) by proposing DSCNet, a framework that leverages dual-stream contrastive learning to incorporate both pixel-wise and semantic-wise contextual information, achieving state-of-the-art results on PASCAL VOC and MS COCO benchmarks.
Weakly supervised semantic segmentation (WSSS) aims at learning a semantic segmentation model with only image-level tags. Despite intensive research on deep learning approaches over a decade, there is still a significant performance gap between WSSS and full semantic segmentation. Most current WSSS methods always focus on a limited single image (pixel-wise) information while ignoring the valuable inter-image (semantic-wise) information. From this perspective, a novel end-to-end WSSS framework called DSCNet is developed along with two innovations: i) pixel-wise group contrast and semantic-wise graph contrast are proposed and introduced into the WSSS framework; ii) a novel dual-stream contrastive learning (DSCL) mechanism is designed to jointly handle pixel-wise and semantic-wise context information for better WSSS performance. Specifically, the pixel-wise group contrast learning (PGCL) and semantic-wise graph contrast learning (SGCL) tasks form a more comprehensive solution. Extensive experiments on PASCAL VOC and MS COCO benchmarks verify the superiority of DSCNet over SOTA approaches and baseline models.