Papers › Hierarchical Dense Correlation Distillation for Few-Shot Segmentation

Hierarchical Dense Correlation Distillation for Few-Shot Segmentation

26 Mar 2023CVPR 2023 1arXiv:2303.14652archive 2025-07-28

Bohao Peng, Zhuotao Tian, Xiaoyang Wu, Chenyao Wang, Shu Liu, Jingyong Su, Jiaya Jia

Few-shot semantic segmentation (FSS) aims to form class-agnostic models segmenting unseen classes with only a handful of annotations. Previous methods limited to the semantic feature and prototype representation suffer from coarse segmentation granularity and train-set overfitting. In this work, we design Hierarchically Decoupled Matching Network (HDMNet) mining pixel-level support correlation based on the transformer architecture. The self-attention modules are used to assist in establishing hierarchical dense features, as a means to accomplish the cascade matching between query and support features. Moreover, we propose a matching module to reduce train-set overfitting and introduce correlation distillation leveraging semantic correspondence from coarse resolution to boost fine-grained segmentation. Our method performs decently in experiments. We achieve 50.0% mIoU on \coco dataset one-shot setting and 56.0% on five-shot segmentation, respectively.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

pbihao/hdmnet officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested 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 SegmentationSegmentationSemantic SegmentationSemantic correspondence

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Semantic Segmentation COCO-20i (1-shot) HDMNet (ResNet-50) FB-IoU 72.2 #11 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (1-shot) HDMNet (ResNet-50) Mean IoU 50 #11 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (1-shot) HDMNet (VGG-16) Mean IoU 45.9 #31 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) HDMNet (ResNet-50) FB-IoU 77.7 #15 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) HDMNet (ResNet-50) Mean IoU 56 #15 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) HDMNet (VGG-16) Mean IoU 52.4 #27 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) HDMNet (ResNet-50) Mean IoU 69.4 #10 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) HDMNet (VGG-16) Mean IoU 65.1 #50 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) HDMNet (ResNet-50) Mean IoU 71.8 #22 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) HDMNet (VGG-16) Mean IoU 69.3 #50 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