Papers › Learning Orthogonal Prototypes for Generalized Few-Shot Semantic Segmentation
Learning Orthogonal Prototypes for Generalized Few-Shot Semantic Segmentation
Sun-Ao Liu, Yiheng Zhang, Zhaofan Qiu, Hongtao Xie, Yongdong Zhang, Ting Yao
Generalized few-shot semantic segmentation (GFSS) distinguishes pixels of base and novel classes from the background simultaneously, conditioning on sufficient data of base classes and a few examples from novel class. A typical GFSS approach has two training phases: base class learning and novel class updating. Nevertheless, such a stand-alone updating process often compromises the well-learnt features and results in performance drop on base classes. In this paper, we propose a new idea of leveraging Projection onto Orthogonal Prototypes (POP), which updates features to identify novel classes without compromising base classes. POP builds a set of orthogonal prototypes, each of which represents a semantic class, and makes the prediction for each class separately based on the features projected onto its prototype. Technically, POP first learns prototypes on base data, and then extends the prototype set to novel classes. The orthogonal constraint of POP encourages the orthogonality between the learnt prototypes and thus mitigates the influence on base class features when generalizing to novel prototypes. Moreover, we capitalize on the residual of feature projection as the background representation to dynamically fit semantic shifting (i.e., background no longer includes the pixels of novel classes in updating phase). Extensive experiments on two benchmarks demonstrate that our POP achieves superior performances on novel classes without sacrificing much accuracy on base classes. Notably, POP outperforms the state-of-the-art fine-tuning by 3.93% overall mIoU on PASCAL-5i in 5-shot scenario.
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 |
|---|---|---|---|---|---|---|---|
| Generalized Few-Shot Semantic Segmentation | COCO-20i (1-shot) | POP(ResNet-50) | Mean Base and Novel | 35.01 | #2 of 6 | Archive leaderboard | report |
| Generalized Few-Shot Semantic Segmentation | COCO-20i (1-shot) | POP(ResNet-50) | Mean IoU | 44.98 | #2 of 6 | Archive leaderboard | report |
| Generalized Few-Shot Semantic Segmentation | COCO-20i (5-shot) | POP(ResNet-50) | Mean Base and Novel | 42.44 | #2 of 5 | Archive leaderboard | report |
| Generalized Few-Shot Semantic Segmentation | COCO-20i (5-shot) | POP(ResNet-50) | Mean IoU | 48.75 | #2 of 5 | Archive leaderboard | report |
| Generalized Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | POP(ResNet-50) | Mean Base and Novel | 54.72 | #3 of 5 | Archive leaderboard | report |
| Generalized Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | POP(ResNet-50) | Mean IoU | 64.77 | #3 of 5 | Archive leaderboard | report |
| Generalized Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | POP(ResNet-50) | Mean Base and Novel | 65.33 | #2 of 6 | Archive leaderboard | report |
| Generalized Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | POP(ResNet-50) | Mean IoU | 70.28 | #2 of 6 | 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