Papers › Few-shot Semantic Segmentation with Support-induced Graph Convolutional Network

Few-shot Semantic Segmentation with Support-induced Graph Convolutional Network

9 Jan 2023arXiv:2301.03194archive 2025-07-28

Jie Liu, Yanqi Bao, Wenzhe Yin, Haochen Wang, Yang Gao, Jan-Jakob Sonke, Efstratios Gavves

Few-shot semantic segmentation (FSS) aims to achieve novel objects segmentation with only a few annotated samples and has made great progress recently. Most of the existing FSS models focus on the feature matching between support and query to tackle FSS. However, the appearance variations between objects from the same category could be extremely large, leading to unreliable feature matching and query mask prediction. To this end, we propose a Support-induced Graph Convolutional Network (SiGCN) to explicitly excavate latent context structure in query images. Specifically, we propose a Support-induced Graph Reasoning (SiGR) module to capture salient query object parts at different semantic levels with a Support-induced GCN. Furthermore, an instance association (IA) module is designed to capture high-order instance context from both support and query instances. By integrating the proposed two modules, SiGCN can learn rich query context representation, and thus being more robust to appearance variations. Extensive experiments on PASCAL-5i and COCO-20i demonstrate that our SiGCN achieves state-of-the-art performance.

PaperPDF

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

Few-Shot Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Semantic Segmentation COCO-20i (1-shot) SiGCN (ResNet-50) FB-IoU 62.7 #56 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (1-shot) SiGCN (ResNet-50) Mean IoU 41.4 #56 of 85 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) SiGCN (ResNet-50) FB-IoU 66.2 #50 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation COCO-20i (5-shot) SiGCN (ResNet-50) Mean IoU 48 #50 of 81 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) SiGCN (ResNet-101) FB-IoU 78.3 #45 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) SiGCN (ResNet-101) Mean IoU 65.7 #45 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) SiGCN (ResNet-50) FB-IoU 77.5 #49 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) SiGCN (ResNet-50) Mean IoU 65.3 #49 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) SiGCN (VGG-16) FB-IoU 73.5 #77 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (1-Shot) SiGCN (VGG-16) Mean IoU 60.8 #77 of 105 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) SiGCN (ResNet-50) FB-IoU 78.3 #55 of 96 Archive leaderboard report
Few-Shot Semantic Segmentation PASCAL-5i (5-Shot) SiGCN (ResNet-50) Mean IoU 68.5 #55 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

GCN

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