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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lai, Qi, Vong, Chi-Man
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916239196028928
author Lai, Qi
Vong, Chi-Man
author_facet Lai, Qi
Vong, Chi-Man
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_04913
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Weakly-supervised Semantic Segmentation via Dual-stream Contrastive Learning of Cross-image Contextual Information
Lai, Qi
Vong, Chi-Man
Computer Vision and Pattern Recognition
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.
title Weakly-supervised Semantic Segmentation via Dual-stream Contrastive Learning of Cross-image Contextual Information
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.04913