Papers › AutoSAM: Adapting SAM to Medical Images by Overloading the Prompt Encoder

AutoSAM: Adapting SAM to Medical Images by Overloading the Prompt Encoder

10 Jun 2023arXiv:2306.06370archive 2025-07-28

Tal Shaharabany, Aviad Dahan, Raja Giryes, Lior Wolf

The recently introduced Segment Anything Model (SAM) combines a clever architecture and large quantities of training data to obtain remarkable image segmentation capabilities. However, it fails to reproduce such results for Out-Of-Distribution (OOD) domains such as medical images. Moreover, while SAM is conditioned on either a mask or a set of points, it may be desirable to have a fully automatic solution. In this work, we replace SAM's conditioning with an encoder that operates on the same input image. By adding this encoder and without further fine-tuning SAM, we obtain state-of-the-art results on multiple medical images and video benchmarks. This new encoder is trained via gradients provided by a frozen SAM. For inspecting the knowledge within it, and providing a lightweight segmentation solution, we also learn to decode it into a mask by a shallow deconvolution network.

PaperPDF

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image SegmentationSegmentationSemantic SegmentationVideo Polyp Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Polyp Segmentation SUN-SEG-Easy (Unseen) AutoSAM Dice 0.753 #5 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Easy (Unseen) AutoSAM S measure 0.815 #5 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Easy (Unseen) AutoSAM Sensitivity 0.672 #5 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Easy (Unseen) AutoSAM mean E-measure 0.855 #5 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Easy (Unseen) AutoSAM mean F-measure 0.774 #5 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Easy (Unseen) AutoSAM weighted F-measure 0.716 #5 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Hard (Unseen) AutoSAM Dice 0.759 #4 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Hard (Unseen) AutoSAM S-Measure 0.822 #4 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Hard (Unseen) AutoSAM Sensitivity 0.726 #4 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Hard (Unseen) AutoSAM mean E-measure 0.866 #4 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Hard (Unseen) AutoSAM mean F-measure 0.764 #4 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Hard (Unseen) AutoSAM weighted F-measure 0.714 #4 of 18 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

SAM

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