Papers › Prototype Mixture Models for Few-shot Semantic Segmentation
Prototype Mixture Models for Few-shot Semantic Segmentation
Boyu Yang, Chang Liu, Bohao Li, Jianbin Jiao, Qixiang Ye
Few-shot segmentation is challenging because objects within the support and query images could significantly differ in appearance and pose. Using a single prototype acquired directly from the support image to segment the query image causes semantic ambiguity. In this paper, we propose prototype mixture models (PMMs), which correlate diverse image regions with multiple prototypes to enforce the prototype-based semantic representation. Estimated by an Expectation-Maximization algorithm, PMMs incorporate rich channel-wised and spatial semantics from limited support images. Utilized as representations as well as classifiers, PMMs fully leverage the semantics to activate objects in the query image while depressing background regions in a duplex manner. Extensive experiments on Pascal VOC and MS-COCO datasets show that PMMs significantly improve upon state-of-the-arts. Particularly, PMMs improve 5-shot segmentation performance on MS-COCO by up to 5.82\% with only a moderate cost for model size and inference speed.
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 |
|---|---|---|---|---|---|---|---|
| Few-Shot Semantic Segmentation | COCO-20i (1-shot) | RPMM (ResNet-50) | Mean IoU | 30.6 | #81 of 85 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (10-shot) | RPMM | Mean IoU | 33.1 | #4 of 4 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (5-shot) | RPMM (ResNet-50) | Mean IoU | 35.5 | #78 of 81 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i -> Pascal VOC (1-shot) | RPMM | Mean IoU | 49.6 | #13 of 13 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i -> Pascal VOC (5-shot) | RPMM | Mean IoU | 53.8 | #12 of 12 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | RPMM (ResNet-50) | Mean IoU | 56.3 | #96 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (10-Shot) | RPMM | Mean IoU | 57.6 | #4 of 4 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | RPMM (ResNet-50) | Mean IoU | 57.3 | #92 of 96 | 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