Papers › FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network
FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network
Huafeng Liu, Pai Peng, Tao Chen, Qiong Wang, Yazhou Yao, Xian-Sheng Hua
Few-shot semantic segmentation is the task of learning to locate each pixel of the novel class in the query image with only a few annotated support images. The current correlation-based methods construct pair-wise feature correlations to establish the many-to-many matching because the typical prototype-based approaches cannot learn fine-grained correspondence relations. However, the existing methods still suffer from the noise contained in naive correlations and the lack of context semantic information in correlations. To alleviate these problems mentioned above, we propose a Feature-Enhanced Context-Aware Network (FECANet). Specifically, a feature enhancement module is proposed to suppress the matching noise caused by inter-class local similarity and enhance the intra-class relevance in the naive correlation. In addition, we propose a novel correlation reconstruction module that encodes extra correspondence relations between foreground and background and multi-scale context semantic features, significantly boosting the encoder to capture a reliable matching pattern. Experiments on PASCAL-5ⁱ and COCO-20ⁱ datasets demonstrate that our proposed FECANet leads to remarkable improvement compared to previous state-of-the-arts, demonstrating its effectiveness.
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) | FECANet (ResNet-50) | FB-IoU | 69.6 | #55 of 85 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (1-shot) | FECANet (ResNet-50) | Mean IoU | 41.6 | #55 of 85 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (1-shot) | FECANet (VGG-16) | FB-IoU | 65.5 | #72 of 85 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (1-shot) | FECANet (VGG-16) | Mean IoU | 35.4 | #72 of 85 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (10-shot) | FECANet (ResNet-50) | Mean IoU | 49.6 | #2 of 4 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (5-shot) | FECANet (ResNet-50) | FB-IoU | 71.1 | #54 of 81 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (5-shot) | FECANet (ResNet-50) | Mean IoU | 47.6 | #54 of 81 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (5-shot) | FECANet (VGG-16) | FB-IoU | 67.7 | #70 of 81 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (5-shot) | FECANet (VGG-16) | Mean IoU | 41.5 | #70 of 81 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | FECANet (ResNet-50) | FB-IoU | 78.7 | #28 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | FECANet (ResNet-50) | Mean IoU | 67.4 | #28 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | FECANet (VGG-16) | FB-IoU | 76.2 | #60 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | FECANet (VGG-16) | Mean IoU | 64.3 | #60 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (10-Shot) | FECANet (ResNet-50) | Mean IoU | 71.5 | #2 of 4 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | FECANet (ResNet-50) | FB-IoU | 80.7 | #43 of 96 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | FECANet (ResNet-50) | Mean IoU | 70 | #43 of 96 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | FECANet (VGG-16) | FB-IoU | 77.6 | #66 of 96 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | FECANet (VGG-16) | Mean IoU | 66.7 | #66 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