Weakly-supervised Semantic Segmentation via Dual-stream Contrastive Learning of Cross-image Contextual Information

TL;DR

This paper introduces DSCNet, a novel weakly-supervised semantic segmentation framework that leverages dual-stream contrastive learning to utilize both pixel-wise and semantic-wise inter-image information, significantly improving performance.

Contribution

The paper proposes a new end-to-end WSSS framework with pixel-wise group contrast and semantic-wise graph contrast, integrating dual-stream contrastive learning for enhanced segmentation accuracy.

Findings

Outperforms state-of-the-art methods on PASCAL VOC and MS COCO datasets.

Demonstrates the effectiveness of dual-stream contrastive learning in WSSS.

Achieves significant performance gains over baseline models.

Abstract

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.