Papers › Masked Cross-image Encoding for Few-shot Segmentation
Masked Cross-image Encoding for Few-shot Segmentation
Wenbo Xu, Huaxi Huang, Ming Cheng, Litao Yu, Qiang Wu, Jian Zhang
Few-shot segmentation (FSS) is a dense prediction task that aims to infer the pixel-wise labels of unseen classes using only a limited number of annotated images. The key challenge in FSS is to classify the labels of query pixels using class prototypes learned from the few labeled support exemplars. Prior approaches to FSS have typically focused on learning class-wise descriptors independently from support images, thereby ignoring the rich contextual information and mutual dependencies among support-query features. To address this limitation, we propose a joint learning method termed Masked Cross-Image Encoding (MCE), which is designed to capture common visual properties that describe object details and to learn bidirectional inter-image dependencies that enhance feature interaction. MCE is more than a visual representation enrichment module; it also considers cross-image mutual dependencies and implicit guidance. Experiments on FSS benchmarks PASCAL-5ⁱ and COCO-20ⁱ demonstrate the advanced meta-learning ability of the proposed method.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
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) | MCE (ResNet-50) | Mean IoU | 44.22 | #38 of 85 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (5-shot) | MCE (ResNet-50) | Mean IoU | 51.04 | #33 of 81 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | MCE (ResNet-50) | FB-IoU | 78.1 | #42 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | MCE (ResNet-50) | Mean IoU | 65.93 | #42 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | MCE (VGG-16) | FB-IoU | 74.51 | #71 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | MCE (VGG-16) | Mean IoU | 62.87 | #71 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | MCE (ResNet-50) | FB-IoU | 81.33 | #42 of 96 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | MCE (ResNet-50) | Mean IoU | 70.03 | #42 of 96 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | MCE (VGG-16) | FB-IoU | 78.2 | #57 of 96 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | MCE (VGG-16) | Mean IoU | 68.21 | #57 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