Papers › PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment

PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment

18 Aug 2019ICCV 2019 10arXiv:1908.06391archive 2025-07-28

Kaixin Wang, Jun Hao Liew, Yingtian Zou, Daquan Zhou, Jiashi Feng

Despite the great progress made by deep CNNs in image semantic segmentation, they typically require a large number of densely-annotated images for training and are difficult to generalize to unseen object categories. Few-shot segmentation has thus been developed to learn to perform segmentation from only a few annotated examples. In this paper, we tackle the challenging few-shot segmentation problem from a metric learning perspective and present PANet, a novel prototype alignment network to better utilize the information of the support set. Our PANet learns class-specific prototype representations from a few support images within an embedding space and then performs segmentation over the query images through matching each pixel to the learned prototypes. With non-parametric metric learning, PANet offers high-quality prototypes that are representative for each semantic class and meanwhile discriminative for different classes. Moreover, PANet introduces a prototype alignment regularization between support and query. With this, PANet fully exploits knowledge from the support and provides better generalization on few-shot segmentation. Significantly, our model achieves the mIoU score of 48.1% and 55.7% on PASCAL-5i for 1-shot and 5-shot settings respectively, surpassing the state-of-the-art method by 1.8% and 8.6%.

PaperPDFConference PDFCode

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

Code

kaixin96/PANet officialmentioned on GitHubpytorch report
LiheYoung/MiningFSS mentioned on GitHubpytorch report
RogerQi/pascal-5i mentioned on GitHubpytorchMIT report
fanq15/ssp mentioned on GitHubpytorchMIT 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

Few-Shot Semantic SegmentationMetric LearningSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Semantic Segmentation COCO-20i (1-shot) PANet (VGG-16) FB-IoU 59.2 #84 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (1-shot) PANet (VGG-16) Mean IoU 20.9 #84 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (2-way 1-shot) PANet (ResNet-50) mIoU 18.0 #6 of 6 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) PANet (VGG-16) FB-IoU 63.5 #79 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) PANet (VGG-16) Mean IoU 29.7 #79 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) PANet (VGG-16) FB-IoU 66.5 #103 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) PANet (VGG-16) Mean IoU 48.1 #103 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) PANet (VGG-16) FB-IoU 70.7 #94 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) PANet (VGG-16) Mean IoU 55.7 #94 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.

Methods

1x1 ConvolutionAdaptive Feature PoolingBottom-up Path AugmentationConvolutionDense ConnectionsFPNPAFPNPANetRPNReLURoIAlign

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