mlsanityData to 7 Oct 2026

SAM-DA: Decoder Adapter for Efficient Medical Domain Adaptation

arXiv 2501.06836 ↗First posted 12 Jan 2025cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

This paper addresses the domain adaptation challenge for semantic segmentation in medical imaging. Despite the impressive performance of recent foundational segmentation models like SAM on natural images, they struggle with medical domain images. Beyond this, recent approaches that perform end-to-end fine-tuning of models are simply not computationally tractable. To address this, we propose a novel SAM adapter approach that minimizes the number of trainable parameters while achieving comparable performances to full fine-tuning. The proposed SAM adapter is strategically placed in the mask decoder, offering excellent and broad generalization capabilities and improved segmentation across both fully supervised and test-time domain adaptation tasks. Extensive validation on four datasets showcases the adapter's efficacy, outperforming existing methods while training less than 1% of SAM's total parameters.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 39 of its 54 references that are in the map. First posted on arXiv 12 Jan 2025.

Builds on

39 of 54 references.

References · 39

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  5. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  6. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  7. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  8. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  9. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  10. 2021Towards a Unified View of Parameter-Efficient Transfer Learningcited by 863
  11. 2020AdapterFusion: Non-Destructive Task Composition for Transfer Learningcited by 780
  12. 2023LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attentioncited by 776
27 more
  1. 2021GPT Understands, Toocited by 715
  2. 2018Taskonomy: Disentangling Task Transfer Learningcited by 631
  3. 2022Vision Transformer Adapter for Dense Predictionscited by 564
  4. 2023Segment Everything Everywhere All at Oncecited by 546
  5. 2023Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentationcited by 485
  6. 2023Segment Anything in High Qualitycited by 373
  7. 2019Transfusion: Understanding Transfer Learning for Medical Imagingcited by 366
  8. 2021Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworkscited by 278
  9. 2023Customized Segment Anything Model for Medical Image Segmentationcited by 277
  10. 2023Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessmentcited by 227
  11. 2023Segment Anything in Medical Imagescited by 226
  12. 2020Universal Source-Free Domain Adaptationcited by 219
  13. 2022MIC: Masked Image Consistency for Context-Enhanced Domain Adaptationcited by 176
  14. 2019FSS-1000: A 1000-Class Dataset for Few-Shot Segmentationcited by 160
  15. 2020Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learningcited by 139
  16. 2020Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domainscited by 124
  17. 2020MS-Net: Multi-Site Network for Improving Prostate Segmentation with Heterogeneous MRI Datacited by 121
  18. 2019Standardized Assessment of Automatic Segmentation of White Matter Hyperintensities and Results of the WMH Segmentation Challengecited by 115
  19. 2022Highly Accurate Dichotomous Image Segmentationcited by 110
  20. 2019Towards High-Resolution Salient Object Detectioncited by 92
  21. 2023A Comprehensive Survey on Segment Anything Model for Vision and Beyondcited by 64
  22. 2022Dual Modality Prompt Tuning for Vision-Language Pre-Trained Modelcited by 51
  23. 2022PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentationcited by 41
  24. 2023Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptationcited by 31
  25. 2023Domain Adaptation for Medical Image Segmentation using Transformation-Invariant Self-Trainingcited by 11
  26. 2024Neural Circuit Diagrams: Robust Diagrams for the Communication, Implementation, and Analysis of Deep Learning Architecturescited by 8
  27. 2023Single Image Test-Time Adaptation for Segmentationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026RobustMedSAM: Degradation-Resilient Medical Image Segmentation via Robust Foundation Model Adaptationcited by 1
  2. 2026Hierarchical Prototype-Memory Adaptation of SAM for Surgical Instrument Segmentationcited by 1
  3. 2026ReG-SAM: Reference Graph-Driven SAM for 2D Foundational Vessel Segmentationcited by 0