Papers › ISIM: Iterative Self-Improved Model for Weakly Supervised Segmentation
ISIM: Iterative Self-Improved Model for Weakly Supervised Segmentation
Cenk Bircanoglu, Nafiz Arica
Weakly Supervised Semantic Segmentation (WSSS) is a challenging task aiming to learn the segmentation labels from class-level labels. In the literature, exploiting the information obtained from Class Activation Maps (CAMs) is widely used for WSSS studies. However, as CAMs are obtained from a classification network, they are interested in the most discriminative parts of the objects, producing non-complete prior information for segmentation tasks. In this study, to obtain more coherent CAMs with segmentation labels, we propose a framework that employs an iterative approach in a modified encoder-decoder-based segmentation model, which simultaneously supports classification and segmentation tasks. As no ground-truth segmentation labels are given, the same model also generates the pseudo-segmentation labels with the help of dense Conditional Random Fields (dCRF). As a result, the proposed framework becomes an iterative self-improved model. The experiments performed with DeepLabv3 and UNet models show a significant gain on the Pascal VOC12 dataset, and the DeepLabv3 application increases the current state-of-the-art metric by %2.5. The implementation associated with the experiments can be found: https://github.com/cenkbircanoglu/isim.
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 | PASCAL VOC 2012 test | ISIM (ResNeSt-200) | Mean IoU | 74.98 | #8 of 60 | Archive leaderboard | report |
| Weakly-Supervised Semantic Segmentation | PASCAL VOC 2012 test | ISIM (ResNet-101) | Mean IoU | 71.45 | #28 of 60 | Archive leaderboard | report |
| Weakly-Supervised Semantic Segmentation | PASCAL VOC 2012 val | ISIM (ResNeSt-200) | Mean IoU | 74.90 | #10 of 73 | Archive leaderboard | report |
| Weakly-Supervised Semantic Segmentation | PASCAL VOC 2012 val | ISIM (ResNet-101) | Mean IoU | 70.51 | #38 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