Papers › DuAT: Dual-Aggregation Transformer Network for Medical Image Segmentation

DuAT: Dual-Aggregation Transformer Network for Medical Image Segmentation

21 Dec 2022arXiv:2212.11677archive 2025-07-28

Feilong Tang, Qiming Huang, Jinfeng Wang, Xianxu Hou, Jionglong Su, Jingxin Liu

Transformer-based models have been widely demonstrated to be successful in computer vision tasks by modelling long-range dependencies and capturing global representations. However, they are often dominated by features of large patterns leading to the loss of local details (e.g., boundaries and small objects), which are critical in medical image segmentation. To alleviate this problem, we propose a Dual-Aggregation Transformer Network called DuAT, which is characterized by two innovative designs, namely, the Global-to-Local Spatial Aggregation (GLSA) and Selective Boundary Aggregation (SBA) modules. The GLSA has the ability to aggregate and represent both global and local spatial features, which are beneficial for locating large and small objects, respectively. The SBA module is used to aggregate the boundary characteristic from low-level features and semantic information from high-level features for better preserving boundary details and locating the re-calibration objects. Extensive experiments in six benchmark datasets demonstrate that our proposed model outperforms state-of-the-art methods in the segmentation of skin lesion images, and polyps in colonoscopy images. In addition, our approach is more robust than existing methods in various challenging situations such as small object segmentation and ambiguous object boundaries.

PaperPDFCode

Code

Barrett-python/DuAT officialmentioned 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

Image SegmentationLesion SegmentationMedical Image SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Lesion Segmentation ISIC 2018 DuAT Mean IoU 0.867 #2 of 17 Archive leaderboard report
Lesion Segmentation ISIC 2018 DuAT mean Dice 0.923 #2 of 17 Archive leaderboard report
Medical Image Segmentation 2018 Data Science Bowl DuAT Dice 0.926 #3 of 10 Archive leaderboard report
Medical Image Segmentation 2018 Data Science Bowl DuAT mIoU 0.870 #3 of 10 Archive leaderboard report
Medical Image Segmentation CVC-ClinicDB DuAT Average MAE 0.006 #9 of 48 Archive leaderboard report
Medical Image Segmentation CVC-ClinicDB DuAT mIoU 0.906 #9 of 48 Archive leaderboard report
Medical Image Segmentation CVC-ClinicDB DuAT mean Dice 0.948 #9 of 48 Archive leaderboard report
Medical Image Segmentation CVC-ColonDB DuAT Average MAE 0.026 #11 of 25 Archive leaderboard report
Medical Image Segmentation CVC-ColonDB DuAT mIoU 0.737 #11 of 25 Archive leaderboard report
Medical Image Segmentation CVC-ColonDB DuAT mean Dice 0.819 #11 of 25 Archive leaderboard report
Medical Image Segmentation ETIS-LARIBPOLYPDB DuAT Average MAE 0.013 #8 of 25 Archive leaderboard report
Medical Image Segmentation ETIS-LARIBPOLYPDB DuAT mIoU 0.746 #8 of 25 Archive leaderboard report
Medical Image Segmentation ETIS-LARIBPOLYPDB DuAT mean Dice 0.822 #8 of 25 Archive leaderboard report
Medical Image Segmentation Kvasir-SEG DuAT Average MAE 0.023 #22 of 58 Archive leaderboard report
Medical Image Segmentation Kvasir-SEG DuAT mIoU 0.876 #22 of 58 Archive leaderboard report
Medical Image Segmentation Kvasir-SEG DuAT mean Dice 0.924 #22 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