A parameter-efficient SAM 3 medical adapter using a Dynamic Expert Router (DER) and Decomposed Parameterized Experts (DPE) to route text/visual features through lightweight experts.
At a glance
| Field | Details |
|---|---|
| Model type | Parameter-efficient medical SAM3 adaptation |
| Research team / organization | Shenzhen Research Institute, The Chinese University of Hong Kong, Shenzhen; University of Science and Technology of China; Nanyang Technological University; Imperial College London (Imperial Global Singapore). |
| Input / modality | Medical image segmentation; the public repository lists Synapse, MMWHS, BTCV and ACDC datasets. |
| Prompt / interaction | Natural-language text prompt combined with image-conditioned expert routing. |
| Code license | The GitHub README says research use only and the repository has no top-level LICENSE in the checked snapshot. SAM 3 base weights remain subject to Meta’s SAM License. The MICCAI paper page lists no code URL, while the public GitHub README calls itself an official implementation. |
📚 Paper and publication
Dual-Adaptive SAM3: Hierarchical Routing over Low-Rank Expert Layers for Parameter-Efficient Medical Image Segmentation — MICCAI 2026, LNCS 16884, pp. 155–164; arXiv:2607.02571.
📦 Checkpoints and access
The project links the gated SAM 3 base checkpoint, but does not list a downloadable DA-SAM3 checkpoint. Its inference example expects a locally produced outputs/da_sam3/best_warmup.pt.
The code, model checkpoint and any required foundation-model checkpoint can have different terms. Review each linked source before use or redistribution.
⚙️ Official setup and inference
1 | git clone https://github.com/Reconsider80/DA-SAM3.git |
⚠️ Version and practical notes
The public implementation does not list a downloadable DA-SAM3 checkpoint. Record the Git revision, SAM 3 base checkpoint, training stage and adapter checkpoint; the paper page and GitHub README currently describe code availability differently.
📜 License
The GitHub README says research use only and the repository has no top-level LICENSE in the checked snapshot. SAM 3 base weights remain subject to Meta’s SAM License. The MICCAI paper page lists no code URL, while the public GitHub README calls itself an official implementation.
Citation: Cite the paper above and the upstream project as directed by its authors. This repository links to the original paper; it does not redistribute the code or weights.
Source pages checked: 27 October 2026. Upstream environments, weights and access policies may change; use the linked project as the source of truth.