Papers › KDAS: Knowledge Distillation via Attention Supervision Framework for Polyp Segmentation

KDAS: Knowledge Distillation via Attention Supervision Framework for Polyp Segmentation

13 Dec 2023arXiv:2312.08555archive 2025-07-28

Quoc-Huy Trinh, Minh-Van Nguyen, Phuoc-Thao Vo Thi

Polyp segmentation, a contentious issue in medical imaging, has seen numerous proposed methods aimed at improving the quality of segmented masks. While current state-of-the-art techniques yield impressive results, the size and computational cost of these models create challenges for practical industry applications. To address this challenge, we present KDAS, a Knowledge Distillation framework that incorporates attention supervision, and our proposed Symmetrical Guiding Module. This framework is designed to facilitate a compact student model with fewer parameters, allowing it to learn the strengths of the teacher model and mitigate the inconsistency between teacher features and student features, a common challenge in Knowledge Distillation, via the Symmetrical Guiding Module. Through extensive experiments, our compact models demonstrate their strength by achieving competitive results with state-of-the-art methods, offering a promising approach to creating compact models with high accuracy for polyp segmentation and in the medical imaging field. The implementation is available on https://github.com/huyquoctrinh/KDAS.

PaperPDFCode

Code

huyquoctrinh/kdas officialmentioned in papermentioned on GitHubpytorch report
huyquoctrinh/kdas3 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

Knowledge DistillationMedical Image SegmentationPolyp SegmentationTransfer Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Medical Image Segmentation CVC-ClinicDB KDAS mIoU 0.872 #33 of 48 Archive leaderboard report
Medical Image Segmentation CVC-ClinicDB KDAS mean Dice 0.925 #33 of 48 Archive leaderboard report
Medical Image Segmentation CVC-ColonDB KDAS Average MAE 0.032 #20 of 25 Archive leaderboard report
Medical Image Segmentation CVC-ColonDB KDAS mIoU 0.679 #20 of 25 Archive leaderboard report
Medical Image Segmentation CVC-ColonDB KDAS mean Dice 0.759 #20 of 25 Archive leaderboard report
Medical Image Segmentation Kvasir-SEG KDAS Average MAE 0.027 #32 of 58 Archive leaderboard report
Medical Image Segmentation Kvasir-SEG KDAS mIoU 0.848 #32 of 58 Archive leaderboard report
Medical Image Segmentation Kvasir-SEG KDAS mean Dice 0.913 #32 of 58 Archive leaderboard report
Polyp Segmentation Kvasir-SEG KDAS mDice 0.913 #2 of 8 Archive leaderboard report
Polyp Segmentation Kvasir-SEG KDAS mIoU 0.848 #2 of 8 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

Knowledge Distillation

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