Papers › Part-aware Prototype Network for Few-shot Semantic Segmentation
Part-aware Prototype Network for Few-shot Semantic Segmentation
Yongfei Liu, Xiangyi Zhang, Songyang Zhang, Xuming He
Few-shot semantic segmentation aims to learn to segment new object classes with only a few annotated examples, which has a wide range of real-world applications. Most existing methods either focus on the restrictive setting of one-way few-shot segmentation or suffer from incomplete coverage of object regions. In this paper, we propose a novel few-shot semantic segmentation framework based on the prototype representation. Our key idea is to decompose the holistic class representation into a set of part-aware prototypes, capable of capturing diverse and fine-grained object features. In addition, we propose to leverage unlabeled data to enrich our part-aware prototypes, resulting in better modeling of intra-class variations of semantic objects. We develop a novel graph neural network model to generate and enhance the proposed part-aware prototypes based on labeled and unlabeled images. Extensive experimental evaluations on two benchmarks show that our method outperforms the prior art with a sizable margin.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_citation_path(paper_1="2007.06309", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2007.06309")
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.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
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) | PPNet (ResNet-50) | Mean IoU | 29.0 | #82 of 85 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (1-shot) | PPNet (ResNet-50) | learnable parameters (million) | 31.5 | #82 of 85 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (2-way 1-shot) | PPNet (ResNet-50) | mIoU | 20.4 | #5 of 6 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (5-shot) | PPNet (ResNet-50) | Mean IoU | 38.5 | #74 of 81 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (5-shot) | PPNet (ResNet-50) | learnable parameters (million) | 31.5 | #74 of 81 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | PPNet (ResNet-50) | Mean IoU | 51.5 | #102 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | PPNet (ResNet-50) | learnable parameters (million) | 31.5 | #102 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | PPNet (ResNet-50) | Mean IoU | 62.0 | #82 of 96 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | PPNet (ResNet-50) | learnable parameters (million) | 31.5 | #82 of 96 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | Pascal5i | PPNet | meanIOU | 55.16 | #3 of 3 | 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