Papers › Stepwise Feature Fusion: Local Guides Global

Stepwise Feature Fusion: Local Guides Global

7 Mar 2022arXiv:2203.03635archive 2025-07-28

Jinfeng Wang, Qiming Huang, Feilong Tang, Jia Meng, Jionglong Su, Sifan Song

Colonoscopy, currently the most efficient and recognized colon polyp detection technology, is necessary for early screening and prevention of colorectal cancer. However, due to the varying size and complex morphological features of colonic polyps as well as the indistinct boundary between polyps and mucosa, accurate segmentation of polyps is still challenging. Deep learning has become popular for accurate polyp segmentation tasks with excellent results. However, due to the structure of polyps image and the varying shapes of polyps, it easy for existing deep learning models to overfitting the current dataset. As a result, the model may not process unseen colonoscopy data. To address this, we propose a new State-Of-The-Art model for medical image segmentation, the SSFormer, which uses a pyramid Transformer encoder to improve the generalization ability of models. Specifically, our proposed Progressive Locality Decoder can be adapted to the pyramid Transformer backbone to emphasize local features and restrict attention dispersion. The SSFormer achieves statet-of-the-art performance in both learning and generalization assessment.

PaperPDFCode

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

Code

Qiming-Huang/ssformer 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

DecoderImage SegmentationMedical Image SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Medical Image Segmentation 2018 Data Science Bowl SSFormer-L Dice 0.9230 #4 of 10 Archive leaderboard report
Medical Image Segmentation 2018 Data Science Bowl SSFormer-L mIoU 0.8614 #4 of 10 Archive leaderboard report
Medical Image Segmentation CVC-ClinicDB SSFormer-L mIoU 0.8995 #15 of 48 Archive leaderboard report
Medical Image Segmentation CVC-ClinicDB SSFormer-L mean Dice 0.9447 #15 of 48 Archive leaderboard report
Medical Image Segmentation CVC-ColonDB SSFormer-L mIoU 0.721 #14 of 25 Archive leaderboard report
Medical Image Segmentation CVC-ColonDB SSFormer-L mean Dice 0.802 #14 of 25 Archive leaderboard report
Medical Image Segmentation ETIS-LARIBPOLYPDB SSFormer-L mIoU 0.720 #10 of 25 Archive leaderboard report
Medical Image Segmentation ETIS-LARIBPOLYPDB SSFormer-L mean Dice 0.796 #10 of 25 Archive leaderboard report
Medical Image Segmentation Kvasir-SEG SSFormer-L mIoU 0.8905 #12 of 58 Archive leaderboard report
Medical Image Segmentation Kvasir-SEG SSFormer-L mean Dice 0.9357 #12 of 58 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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