Papers › RecurSeed and EdgePredictMix: Pseudo-Label Refinement Learning for Weakly Supervised...
RecurSeed and EdgePredictMix: Pseudo-Label Refinement Learning for Weakly Supervised Semantic Segmentation across Single- and Multi-Stage Frameworks
Sanghyun Jo, In-Jae Yu, KyungSu Kim
Although weakly supervised semantic segmentation using only image-level labels (WSSS-IL) is potentially useful, its low performance and implementation complexity still limit its application. The main causes are (a) non-detection and (b) false-detection phenomena: (a) The class activation maps refined from existing WSSS-IL methods still only represent partial regions for large-scale objects, and (b) for small-scale objects, over-activation causes them to deviate from the object edges. We propose RecurSeed, which alternately reduces non- and false detections through recursive iterations, thereby implicitly finding an optimal junction that minimizes both errors. We also propose a novel data augmentation (DA) approach called EdgePredictMix, which further expresses an object's edge by utilizing the probability difference information between adjacent pixels in combining the segmentation results, thereby compensating for the shortcomings when applying the existing DA methods to WSSS. We achieved new state-of-the-art performances on both the PASCAL VOC 2012 and MS COCO 2014 benchmarks (VOC val: 74.4%, COCO val: 46.4%). The code is available at https://github.com/shjo-april/RecurSeed_and_EdgePredictMix.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
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 | RS+EPM (ResNet-101, multi-stage) | mIoU | 46.4 | #10 of 39 | Archive leaderboard | report |
| Weakly-Supervised Semantic Segmentation | COCO 2014 val | RS+EPM (ResNet-50, single-stage) | mIoU | 42.2 | #22 of 39 | Archive leaderboard | report |
| Weakly-Supervised Semantic Segmentation | PASCAL VOC 2012 test | RS+EPM (ResNet-101, multi-stage) | Mean IoU | 73.6 | #14 of 60 | Archive leaderboard | report |
| Weakly-Supervised Semantic Segmentation | PASCAL VOC 2012 test | RS+EPM (ResNet-50, single-stage) | Mean IoU | 70.6 | #40 of 60 | Archive leaderboard | report |
| Weakly-Supervised Semantic Segmentation | PASCAL VOC 2012 val | RS+EPM (ResNet-101, multi-stage) | Mean IoU | 74.4 | #11 of 73 | Archive leaderboard | report |
| Weakly-Supervised Semantic Segmentation | PASCAL VOC 2012 val | RS+EPM (ResNet-50, single-stage) | Mean IoU | 69.5 | #48 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