Papers › Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling
Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling
Lixiang Ru, Bo Du, Yibing Zhan, Chen Wu
Weakly-Supervised Semantic Segmentation (WSSS) methods with image-level labels generally train a classification network to generate the Class Activation Maps (CAMs) as the initial coarse segmentation labels. However, current WSSS methods still perform far from satisfactorily because their adopted CAMs 1) typically focus on partial discriminative object regions and 2) usually contain useless background regions. These two problems are attributed to the sole image-level supervision and aggregation of global information when training the classification networks. In this work, we propose the visual words learning module and hybrid pooling approach, and incorporate them in the classification network to mitigate the above problems. In the visual words learning module, we counter the first problem by enforcing the classification network to learn fine-grained visual word labels so that more object extents could be discovered. Specifically, the visual words are learned with a codebook, which could be updated via two proposed strategies, i.e. learning-based strategy and memory-bank strategy. The second drawback of CAMs is alleviated with the proposed hybrid pooling, which incorporates the global average and local discriminative information to simultaneously ensure object completeness and reduce background regions. We evaluated our methods on PASCAL VOC 2012 and MS COCO 2014 datasets. Without any extra saliency prior, our method achieved 70.6% and 70.7% mIoU on the val and test set of PASCAL VOC dataset, respectively, and 36.2% mIoU on the val set of MS COCO dataset, which significantly surpassed the performance of state-of-the-art WSSS methods.
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 | VWL-L | mIoU | 36.2 | #32 of 39 | Archive leaderboard | report |
| Weakly-Supervised Semantic Segmentation | COCO 2014 val | VWL-M | mIoU | 36.1 | #33 of 39 | Archive leaderboard | report |
| Weakly-Supervised Semantic Segmentation | PASCAL VOC 2012 test | VWL-L (EMANet) | Mean IoU | 71.1 | #29 of 60 | Archive leaderboard | report |
| Weakly-Supervised Semantic Segmentation | PASCAL VOC 2012 test | VWL-L | Mean IoU | 70.7 | #36 of 60 | Archive leaderboard | report |
| Weakly-Supervised Semantic Segmentation | PASCAL VOC 2012 test | VWL-M | Mean IoU | 70.4 | #42 of 60 | Archive leaderboard | report |
| Weakly-Supervised Semantic Segmentation | PASCAL VOC 2012 val | VWL-L (EMANet) | Mean IoU | 70.8 | #33 of 73 | Archive leaderboard | report |
| Weakly-Supervised Semantic Segmentation | PASCAL VOC 2012 val | VWL-L | Mean IoU | 70.6 | #36 of 73 | Archive leaderboard | report |
| Weakly-Supervised Semantic Segmentation | PASCAL VOC 2012 val | VWL-M | Mean IoU | 70.6 | #37 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