mlsanityData to 13 Oct 2026

Efficient Self-Supervised Adaptation for Medical Image Analysis

arXiv 2503.18873 ↗First posted 24 Mar 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Self-supervised adaptation (SSA) improves foundation model transfer to medical domains but is computationally prohibitive. Although parameter efficient fine-tuning methods such as LoRA have been explored for supervised adaptation, their effectiveness for SSA remains unknown. In this work, we introduce efficient self-supervised adaptation (ESSA), a framework that applies parameter-efficient fine-tuning techniques to SSA with the aim of reducing computational cost and improving adaptation performance. Among the methods tested, Attention Projection Layer Adaptation (APLA) sets a new state-of-the-art, consistently surpassing full-parameter SSA and supervised fine-tuning across diverse medical tasks, while reducing GPU memory by up to 40.1% and increasing training throughput by 25.2%, all while maintaining inference efficiency.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 25 of its 37 references that are in the map. First posted on arXiv 24 Mar 2025.

Builds on

25 of 37 references.

References · 25

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,043
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,231
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,857
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,915
  5. 2021On the Opportunities and Risks of Foundation Modelscited by 3,999
  6. 2022Visual Prompt Tuningcited by 1,677
  7. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,369
  8. 2021BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-modelscited by 1,240
  9. 2023Scaling Vision Transformers to 22 Billion Parameterscited by 693
  10. 2019Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)cited by 664
  11. 2019Transfusion: Understanding Transfer Learning for Medical Imagingcited by 367
  12. 2021Big Self-Supervised Models Advance Medical Image Classificationcited by 320
13 more
  1. 2022Test-Time Training with Masked Autoencoderscited by 209
  2. 2022Delving into Masked Autoencoders for Multi-Label Thorax Disease Classificationcited by 65
  3. 2022What Makes Transfer Learning Work For Medical Images: Feature Reuse & Other Factorscited by 61
  4. 2021Is it Time to Replace CNNs with Transformers for Medical Images?cited by 60
  5. 2019Self-supervised Domain Adaptation for Computer Vision Taskscited by 58
  6. 2023Parameter-Efficient Fine-Tuning for Medical Image Analysis: The Missed Opportunitycited by 55
  7. 2023Are Natural Domain Foundation Models Useful for Medical Image Classification?cited by 45
  8. 2024EndoDAC: Efficient Adapting Foundation Model for Self-Supervised Depth Estimation from Any Endoscopic Cameracited by 43
  9. 2023MeLo: Low-rank Adaptation is Better than Fine-tuning for Medical Image Diagnosiscited by 33
  10. 2023Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectivescited by 24
  11. 2024Less Could Be Better: Parameter-efficient Fine-tuning Advances Medical Vision Foundation Modelscited by 18
  12. 2023Pretrained ViTs Yield Versatile Representations For Medical Imagescited by 13
  13. 2025APLA: A Simple Adaptation Method for Vision Transformerscited by 1

Built on by

Not cited yet.