Papers › FANet: A Feedback Attention Network for Improved Biomedical Image Segmentation

FANet: A Feedback Attention Network for Improved Biomedical Image Segmentation

31 Mar 2021arXiv:2103.17235archive 2025-07-28

Nikhil Kumar Tomar, Debesh Jha, Michael A. Riegler, Håvard D. Johansen, Dag Johansen, Jens Rittscher, Pål Halvorsen, Sharib Ali

The increase of available large clinical and experimental datasets has contributed to a substantial amount of important contributions in the area of biomedical image analysis. Image segmentation, which is crucial for any quantitative analysis, has especially attracted attention. Recent hardware advancement has led to the success of deep learning approaches. However, although deep learning models are being trained on large datasets, existing methods do not use the information from different learning epochs effectively. In this work, we leverage the information of each training epoch to prune the prediction maps of the subsequent epochs. We propose a novel architecture called feedback attention network (FANet) that unifies the previous epoch mask with the feature map of the current training epoch. The previous epoch mask is then used to provide a hard attention to the learned feature maps at different convolutional layers. The network also allows to rectify the predictions in an iterative fashion during the test time. We show that our proposed \textit{feedback attention} model provides a substantial improvement on most segmentation metrics tested on seven publicly available biomedical imaging datasets demonstrating the effectiveness of FANet. The source code is available at \url{https://github.com/nikhilroxtomar/FANet}.

PaperPDFCode

Code

nikhilroxtomar/fanet 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

Hard AttentionImage SegmentationMedical Image SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Medical Image Segmentation 2018 Data Science Bowl FANet Dice 0.9176 #7 of 10 Archive leaderboard report
Medical Image Segmentation 2018 Data Science Bowl FANet Precision 0.9194 #7 of 10 Archive leaderboard report
Medical Image Segmentation 2018 Data Science Bowl FANet Recall 0.9222 #7 of 10 Archive leaderboard report
Medical Image Segmentation 2018 Data Science Bowl FANet mIoU 0.8569 #7 of 10 Archive leaderboard report
Medical Image Segmentation CHASE_DB1 FANet DSC 0.8108 #3 of 3 Archive leaderboard report
Medical Image Segmentation CVC-ClinicDB FANet mean Dice 0.9355 #26 of 48 Archive leaderboard report
Medical Image Segmentation DRIVE FANet F1 score 0.8183 #3 of 5 Archive leaderboard report
Medical Image Segmentation DRIVE FANet Precision 0.8189 #3 of 5 Archive leaderboard report
Medical Image Segmentation DRIVE FANet Recall 0.8215 #3 of 5 Archive leaderboard report
Medical Image Segmentation DRIVE FANet Specificity 0.9826 #3 of 5 Archive leaderboard report
Medical Image Segmentation DRIVE FANet mIoU 0.6927 #3 of 5 Archive leaderboard report
Medical Image Segmentation EM FANet DSC 0.9547 #2 of 3 Archive leaderboard report
Medical Image Segmentation EM FANet IoU 0.9134 #2 of 3 Archive leaderboard report
Medical Image Segmentation EM FANet Precision 0.9529 #2 of 3 Archive leaderboard report
Medical Image Segmentation EM FANet Recall 0.9568 #2 of 3 Archive leaderboard report
Medical Image Segmentation EM FANet Specificity 0.8096 #2 of 3 Archive leaderboard report
Medical Image Segmentation ISIC 2018 FANet DSC 87.31 #5 of 5 Archive leaderboard report
Medical Image Segmentation Kvasir-SEG FANet Average MAE 0.8153 #47 of 58 Archive leaderboard report
Medical Image Segmentation Kvasir-SEG FANet mean Dice 0.8803 #47 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.

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