Papers › Full-scale Representation Guided Network for Retinal Vessel Segmentation

Full-scale Representation Guided Network for Retinal Vessel Segmentation

31 Jan 2025arXiv:2501.18921archive 2025-07-28

Sunyong Seo, Huisu Yoon, Semin Kim, Jongha Lee

The U-Net architecture and its variants have remained state-of-the-art (SOTA) for retinal vessel segmentation over the past decade. In this study, we introduce a Full Scale Guided Network (FSG-Net), where the feature representation network with modernized convolution blocks extracts full-scale information and the guided convolution block refines that information. Attention-guided filter is introduced to the guided convolution block under the interpretation that the filter behaves like the unsharp mask filter. Passing full-scale information to the attention block allows for the generation of improved attention maps, which are then passed to the attention-guided filter, resulting in performance enhancement of the segmentation network. The structure preceding the guided convolution block can be replaced by any U-Net variant, which enhances the scalability of the proposed approach. For a fair comparison, we re-implemented recent studies available in public repositories to evaluate their scalability and reproducibility. Our experiments also show that the proposed network demonstrates competitive results compared to current SOTA models on various public datasets. Ablation studies demonstrate that the proposed model is competitive with much smaller parameter sizes. Lastly, by applying the proposed model to facial wrinkle segmentation, we confirmed the potential for scalability to similar tasks in other domains. Our code is available on https://github.com/ZombaSY/FSG-Net-pytorch.

PaperPDFCode

Code

zombasy/fsg-net-pytorch officialmentioned in papermentioned on GitHubpytorch 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

Retinal Vessel Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Retinal Vessel Segmentation CHASE_DB1 FSG-Net AUC 0.9937 #1 of 16 Archive leaderboard report
Retinal Vessel Segmentation CHASE_DB1 FSG-Net Acc 0.9751 #1 of 16 Archive leaderboard report
Retinal Vessel Segmentation CHASE_DB1 FSG-Net F1 score 0.8101 #1 of 16 Archive leaderboard report
Retinal Vessel Segmentation CHASE_DB1 FSG-Net MCC 0.7989 #1 of 16 Archive leaderboard report
Retinal Vessel Segmentation CHASE_DB1 FSG-Net Sensitivity 0.8599 #1 of 16 Archive leaderboard report
Retinal Vessel Segmentation CHASE_DB1 FSG-Net mIOU 0.8268 #1 of 16 Archive leaderboard report
Retinal Vessel Segmentation DRIVE FSG-Net AUC 0.9823 #8 of 22 Archive leaderboard report
Retinal Vessel Segmentation DRIVE FSG-Net Accuracy 0.9704 #8 of 22 Archive leaderboard report
Retinal Vessel Segmentation DRIVE FSG-Net F1 score 0.8322 #8 of 22 Archive leaderboard report
Retinal Vessel Segmentation DRIVE FSG-Net MCC 0.8173 #8 of 22 Archive leaderboard report
Retinal Vessel Segmentation DRIVE FSG-Net mIoU 0.8406 #8 of 22 Archive leaderboard report
Retinal Vessel Segmentation DRIVE FSG-Net sensitivity 0.8420 #8 of 22 Archive leaderboard report
Retinal Vessel Segmentation HRF FSG-Net AUC 0.9874 #1 of 4 Archive leaderboard report
Retinal Vessel Segmentation HRF FSG-Net Acc 0.9710 #1 of 4 Archive leaderboard report
Retinal Vessel Segmentation HRF FSG-Net F1 score 0.8156 #1 of 4 Archive leaderboard report
Retinal Vessel Segmentation HRF FSG-Net MCC 0.8012 #1 of 4 Archive leaderboard report
Retinal Vessel Segmentation HRF FSG-Net Sensitivity 0.8361 #1 of 4 Archive leaderboard report
Retinal Vessel Segmentation HRF FSG-Net mIoU 0.8308 #1 of 4 Archive leaderboard report
Retinal Vessel Segmentation STARE FSG-Net AUC 0.9896 #3 of 10 Archive leaderboard report
Retinal Vessel Segmentation STARE FSG-Net Acc 0.9774 #3 of 10 Archive leaderboard report
Retinal Vessel Segmentation STARE FSG-Net F1 score 0.8510 #3 of 10 Archive leaderboard report
Retinal Vessel Segmentation STARE FSG-Net MCC 0.8395 #3 of 10 Archive leaderboard report
Retinal Vessel Segmentation STARE FSG-Net Sensitivity 0.8660 #3 of 10 Archive leaderboard report
Retinal Vessel Segmentation STARE FSG-Net mIOU 0.8611 #3 of 10 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

AttentionConcatenated Skip ConnectionConvolutionMax PoolingReLUSoftmaxU-Net

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