Papers › Weakly Supervised Co-training with Swapping Assignments for Semantic Segmentation
Weakly Supervised Co-training with Swapping Assignments for Semantic Segmentation
Xinyu Yang, Hossein Rahmani, Sue Black, Bryan M. Williams
Class activation maps (CAMs) are commonly employed in weakly supervised semantic segmentation (WSSS) to produce pseudo-labels. Due to incomplete or excessive class activation, existing studies often resort to offline CAM refinement, introducing additional stages or proposing offline modules. This can cause optimization difficulties for single-stage methods and limit generalizability. In this study, we aim to reduce the observed CAM inconsistency and error to mitigate reliance on refinement processes. We propose an end-to-end WSSS model incorporating guided CAMs, wherein our segmentation model is trained while concurrently optimizing CAMs online. Our method, Co-training with Swapping Assignments (CoSA), leverages a dual-stream framework, where one sub-network learns from the swapped assignments generated by the other. We introduce three techniques: i) soft perplexity-based regularization to penalize uncertain regions; ii) a threshold-searching approach to dynamically revise the confidence threshold; and iii) contrastive separation to address the coexistence problem. CoSA demonstrates exceptional performance, achieving mIoU of 76.2\% and 51.0\% on VOC and COCO validation datasets, respectively, surpassing existing baselines by a substantial margin. Notably, CoSA is the first single-stage approach to outperform all existing multi-stage methods including those with additional supervision. Code is avilable at \url{https://github.com/youshyee/CoSA}.
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 | CoSA (SWIN-B, multi-stage) | mIoU | 53.7 | #5 of 39 | Archive leaderboard | report |
| Weakly-Supervised Semantic Segmentation | COCO 2014 val | CoSA (ViT-B, single-stage) | mIoU | 51.1 | #6 of 39 | Archive leaderboard | report |
| Weakly-Supervised Semantic Segmentation | PASCAL VOC 2012 val | CoSA (SWIN-B, multi-stage) | Mean IoU | 81.4 | #4 of 73 | Archive leaderboard | report |
| Weakly-Supervised Semantic Segmentation | PASCAL VOC 2012 val | CoSA (ViT-B, single-stage) | Mean IoU | 76.4 | #8 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.
Methods
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