Papers › Adaptive Prototype Learning and Allocation for Few-Shot Segmentation

Adaptive Prototype Learning and Allocation for Few-Shot Segmentation

5 Apr 2021CVPR 2021 1arXiv:2104.01893archive 2025-07-28

Gen Li, Varun Jampani, Laura Sevilla-Lara, Deqing Sun, Jonghyun Kim, Joongkyu Kim

Prototype learning is extensively used for few-shot segmentation. Typically, a single prototype is obtained from the support feature by averaging the global object information. However, using one prototype to represent all the information may lead to ambiguities. In this paper, we propose two novel modules, named superpixel-guided clustering (SGC) and guided prototype allocation (GPA), for multiple prototype extraction and allocation. Specifically, SGC is a parameter-free and training-free approach, which extracts more representative prototypes by aggregating similar feature vectors, while GPA is able to select matched prototypes to provide more accurate guidance. By integrating the SGC and GPA together, we propose the Adaptive Superpixel-guided Network (ASGNet), which is a lightweight model and adapts to object scale and shape variation. In addition, our network can easily generalize to k-shot segmentation with substantial improvement and no additional computational cost. In particular, our evaluations on COCO demonstrate that ASGNet surpasses the state-of-the-art method by 5% in 5-shot segmentation.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Reagan1311/ASGNet officialmentioned on GitHubpytorch report
Meidianwen/few_shot_segmentation mentioned on GitHubpytorch report

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

ClusteringFew-Shot Semantic SegmentationSegmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Semantic Segmentation COCO-20i (1-shot) ASGNet (ResNet-50) FB-IoU 60.39 #74 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (1-shot) ASGNet (ResNet-50) Mean IoU 34.56 #74 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) ASGNet (ResNet-50) FB-IoU 66.96 #67 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) ASGNet (ResNet-50) Mean IoU 42.48 #67 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) ASGNet (ResNet-101) FB-IoU 71.7 #86 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) ASGNet (ResNet-101) Mean IoU 59.31 #86 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) ASGNet (ResNet-50) FB-IoU 69.2 #87 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) ASGNet (ResNet-50) Mean IoU 59.29 #87 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) ASGNet (ResNet-101) FB-IoU 75.2 #75 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) ASGNet (ResNet-101) Mean IoU 64.36 #75 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) ASGNet (ResNet-50) FB-IoU 74.2 #78 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) ASGNet (ResNet-50) Mean IoU 63.94 #78 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