# Efficient Self-Supervised Adaptation for Medical Image Analysis

arXiv: https://arxiv.org/abs/2503.18873 · HTML: https://mlsanity.com/paper/2503.18873/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 37 references that are in the map.
- First posted on arXiv 24 Mar 2025.

## Builds on (most cited first, 25 of 25)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [Scaling Vision Transformers to 22 Billion Parameters](https://mlsanity.com/paper/2302.05442/) (2023)
- [Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1902.03368/) (2019)
- [Transfusion: Understanding Transfer Learning for Medical Imaging](https://mlsanity.com/paper/1902.07208/) (2019)
- [Big Self-Supervised Models Advance Medical Image Classification](https://mlsanity.com/paper/2101.05224/) (2021)
- [Test-Time Training with Masked Autoencoders](https://mlsanity.com/paper/2209.07522/) (2022)
- [Delving into Masked Autoencoders for Multi-Label Thorax Disease Classification](https://mlsanity.com/paper/2210.12843/) (2022)
- [What Makes Transfer Learning Work For Medical Images: Feature Reuse & Other Factors](https://mlsanity.com/paper/2203.01825/) (2022)
- [Is it Time to Replace CNNs with Transformers for Medical Images?](https://mlsanity.com/paper/2108.09038/) (2021)
- [Self-supervised Domain Adaptation for Computer Vision Tasks](https://mlsanity.com/paper/1907.10915/) (2019)
- [Parameter-Efficient Fine-Tuning for Medical Image Analysis: The Missed Opportunity](https://mlsanity.com/paper/2305.08252/) (2023)
- [Are Natural Domain Foundation Models Useful for Medical Image Classification?](https://mlsanity.com/paper/2310.19522/) (2023)
- [EndoDAC: Efficient Adapting Foundation Model for Self-Supervised Depth Estimation from Any Endoscopic Camera](https://mlsanity.com/paper/2405.08672/) (2024)
- [MeLo: Low-rank Adaptation is Better than Fine-tuning for Medical Image Diagnosis](https://mlsanity.com/paper/2311.08236/) (2023)
- [Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectives](https://mlsanity.com/paper/2308.01265/) (2023)
- [Less Could Be Better: Parameter-efficient Fine-tuning Advances Medical Vision Foundation Models](https://mlsanity.com/paper/2401.12215/) (2024)
- [Pretrained ViTs Yield Versatile Representations For Medical Images](https://mlsanity.com/paper/2303.07034/) (2023)
- [APLA: A Simple Adaptation Method for Vision Transformers](https://mlsanity.com/paper/2503.11335/) (2025)

## 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.