Papers › Prior Guided Feature Enrichment Network for Few-Shot Segmentation
Prior Guided Feature Enrichment Network for Few-Shot Segmentation
Zhuotao Tian, Hengshuang Zhao, Michelle Shu, Zhicheng Yang, Ruiyu Li, Jiaya Jia
State-of-the-art semantic segmentation methods require sufficient labeled data to achieve good results and hardly work on unseen classes without fine-tuning. Few-shot segmentation is thus proposed to tackle this problem by learning a model that quickly adapts to new classes with a few labeled support samples. Theses frameworks still face the challenge of generalization ability reduction on unseen classes due to inappropriate use of high-level semantic information of training classes and spatial inconsistency between query and support targets. To alleviate these issues, we propose the Prior Guided Feature Enrichment Network (PFENet). It consists of novel designs of (1) a training-free prior mask generation method that not only retains generalization power but also improves model performance and (2) Feature Enrichment Module (FEM) that overcomes spatial inconsistency by adaptively enriching query features with support features and prior masks. Extensive experiments on PASCAL-5ⁱ and COCO prove that the proposed prior generation method and FEM both improve the baseline method significantly. Our PFENet also outperforms state-of-the-art methods by a large margin without efficiency loss. It is surprising that our model even generalizes to cases without labeled support samples. Our code is available at https://github.com/Jia-Research-Lab/PFENet/.
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) | PFENet (VGG-16) | FB-IoU | 60 | #75 of 85 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (1-shot) | PFENet (VGG-16) | Mean IoU | 34.1 | #75 of 85 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (1-shot) | PFENet (ResNet-101) | FB-IoU | 58.6 | #79 of 85 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (1-shot) | PFENet (ResNet-101) | Mean IoU | 32.4 | #79 of 85 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (1-shot) | PFENet (ResNet-101) | learnable parameters (million) | 10.3 | #79 of 85 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (5-shot) | PFENet (VGG-16) | FB-IoU | 61.6 | #75 of 81 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (5-shot) | PFENet (VGG-16) | Mean IoU | 37.7 | #75 of 81 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (5-shot) | PFENet (ResNet-101) | FB-IoU | 61.9 | #76 of 81 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (5-shot) | PFENet (ResNet-101) | Mean IoU | 37.4 | #76 of 81 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (5-shot) | PFENet (ResNet-101) | learnable parameters (million) | 10.3 | #76 of 81 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | PFENet (ResNet-50) | FB-IoU | 73.3 | #78 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | PFENet (ResNet-50) | Mean IoU | 60.8 | #78 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | PFENet (ResNet-50) | learnable parameters (million) | 10.3 | #78 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | PFENet (ResNet-101) | FB-IoU | 72.9 | #82 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | PFENet (ResNet-101) | Mean IoU | 60.1 | #82 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | PFENet (ResNet-101) | learnable parameters (million) | 10.3 | #82 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | PFENet (VGG-16) | FB-IoU | 72 | #90 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | PFENet (VGG-16) | Mean IoU | 58 | #90 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | PFENet (ResNet-50) | FB-IoU | 73.9 | #83 of 96 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | PFENet (ResNet-50) | Mean IoU | 61.9 | #83 of 96 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | PFENet (ResNet-50) | learnable parameters (million) | 10.3 | #83 of 96 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | PFENet (ResNet-101) | FB-IoU | 73.5 | #84 of 96 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | PFENet (ResNet-101) | Mean IoU | 61.4 | #84 of 96 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | PFENet (ResNet-101) | learnable parameters (million) | 10.3 | #84 of 96 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | PFENet (VGG-16) | FB-IoU | 72.3 | #89 of 96 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | PFENet (VGG-16) | Mean IoU | 59 | #89 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