Papers › Dense Gaussian Processes for Few-Shot Segmentation
Dense Gaussian Processes for Few-Shot Segmentation
Joakim Johnander, Johan Edstedt, Michael Felsberg, Fahad Shahbaz Khan, Martin Danelljan
Few-shot segmentation is a challenging dense prediction task, which entails segmenting a novel query image given only a small annotated support set. The key problem is thus to design a method that aggregates detailed information from the support set, while being robust to large variations in appearance and context. To this end, we propose a few-shot segmentation method based on dense Gaussian process (GP) regression. Given the support set, our dense GP learns the mapping from local deep image features to mask values, capable of capturing complex appearance distributions. Furthermore, it provides a principled means of capturing uncertainty, which serves as another powerful cue for the final segmentation, obtained by a CNN decoder. Instead of a one-dimensional mask output, we further exploit the end-to-end learning capabilities of our approach to learn a high-dimensional output space for the GP. Our approach sets a new state-of-the-art on the PASCAL-5ⁱ and COCO-20ⁱ benchmarks, achieving an absolute gain of +8.4 mIoU in the COCO-20ⁱ 5-shot setting. Furthermore, the segmentation quality of our approach scales gracefully when increasing the support set size, while achieving robust cross-dataset transfer. Code and trained models are available at \url{https://github.com/joakimjohnander/dgpnet}.
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) | DGPNet (ResNet-101) | Mean IoU | 46.7 | #22 of 85 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (1-shot) | DGPNet (ResNet-50) | Mean IoU | 45 | #35 of 85 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (10-shot) | DGPNet (ResNet-101) | Mean IoU | 60.2 | #1 of 4 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (5-shot) | DGPNet (ResNet-101) | Mean IoU | 57.9 | #9 of 81 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i (5-shot) | DGPNet (ResNet-50) | Mean IoU | 56.2 | #14 of 81 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i -> Pascal VOC (1-shot) | DGPNet (ResNet-101) | Mean IoU | 70.1 | #3 of 13 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i -> Pascal VOC (1-shot) | DGPNet (ResNet-50) | Mean IoU | 68.9 | #6 of 13 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i -> Pascal VOC (5-shot) | DGPNet (ResNet-101) | Mean IoU | 78.5 | #2 of 12 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | COCO-20i -> Pascal VOC (5-shot) | DGPNet (ResNet-50) | Mean IoU | 77.5 | #3 of 12 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | DGPNet (ResNet-101) | Mean IoU | 64.8 | #53 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (1-Shot) | DGPNet (ResNet-50) | Mean IoU | 63.5 | #67 of 105 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (10-Shot) | DGPNet (ResNet-101) | Mean IoU | 77.7 | #1 of 4 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | DGPNet (ResNet-101) | Mean IoU | 75.4 | #5 of 96 | Archive leaderboard | report |
| Few-Shot Semantic Segmentation | PASCAL-5i (5-Shot) | DGPNet (ResNet-50) | Mean IoU | 73.5 | #13 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
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