Papers › Boundary-Enhanced Co-Training for Weakly Supervised Semantic Segmentation
Boundary-Enhanced Co-Training for Weakly Supervised Semantic Segmentation
Shenghai Rong, Bohai Tu, Zilei Wang, Junjie Li
The existing weakly supervised semantic segmentation (WSSS) methods pay much attention to generating accurate and complete class activation maps (CAMs) as pseudo-labels, while ignoring the importance of training the segmentation networks. In this work, we observe that there is an inconsistency between the quality of the pseudo-labels in CAMs and the performance of the final segmentation model, and the mislabeled pixels mainly lie on the boundary areas. Inspired by these findings, we argue that the focus of WSSS should be shifted to robust learning given the noisy pseudo-labels, and further propose a boundary-enhanced co-training (BECO) method for training the segmentation model. To be specific, we first propose to use a co-training paradigm with two interactive networks to improve the learning of uncertain pixels. Then we propose a boundary-enhanced strategy to boost the prediction of difficult boundary areas, which utilizes reliable predictions to construct artificial boundaries. Benefiting from the design of co-training and boundary enhancement, our method can achieve promising segmentation performance for different CAMs. Extensive experiments on PASCAL VOC 2012 and MS COCO 2014 validate the superiority of our BECO over other state-of-the-art methods.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Weakly-Supervised Semantic Segmentation | COCO 2014 val | BECO(DeepLabV3Plus+R101) | mIoU | 45.1 | #15 of 39 | Archive leaderboard | report |
| Weakly-Supervised Semantic Segmentation | PASCAL VOC 2012 test | BECO(DeepLabV3Plus+MiT-B2) | Mean IoU | 73.5 | #16 of 60 | Archive leaderboard | report |
| Weakly-Supervised Semantic Segmentation | PASCAL VOC 2012 val | BECO(DeepLabV3Plus+MiT-B2) | Mean IoU | 73.7 | #15 of 73 | Archive leaderboard | report |
| Weakly-Supervised Semantic Segmentation | PASCAL VOC 2012 val | BECO(DeepLabV3Plus+R101) | Mean IoU | 72.1 | #21 of 73 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections