Awesome-Medical-Efficient-Fine-Tuning

This repository contains a list of papers on the Efficient Fine-tuning (EFT) on Medical Image Analysis/Computer Vision, we categorize them based on their published years. We will continue to update this list. If you find any error or any missed paper, please don't hesitate to open issues or pull requests. 💗💗💗

Keywords Convention

The main architecture targeted by the method.

The main task targeted by the method.

The type of method.

Review

1. [Medical][MIDL][2024] Parameter-Efficient Fine-Tuning for Medical Image Analysis: The Missed Opportunity [paper] [None]
2. [CV][ACM Computing Surveys][2023] Visual Tuning [paper] [None]
3. [CV][ArXiV][2024] Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey [paper] [code]

Year 2024

1. [CV][ArXiV] Low-rank Attention Side-Tuning for Parameter-Efficient Fine-Tuning [paper] [None]
2. [Medical][MIDL2024] Med-Tuning: A New Parameter-Efficient Tuning Framework for Medical Volumetric Segmentation [paper] [code]
3. [CV][ArXiV] MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning [paper] [code]
4. [CV][ArXiV] Revisiting the Power of Prompt for Visual Tuning [paper] [code]
5. [CV/Video][ArXiV][2024] Time-, Memory- and Parameter-Efficient Visual Adaptation [paper] [None]
6. [CV ][NeurIPS][2024] Efficient Adaptation of Large Vision Transformer via Adapter Re-Composing [paper] [code]
7. [CV][CVPR][2024] Conv-Adapter: Exploring Parameter Efficient Transfer Learning for ConvNets [paper] [code]
8. [Medical][ArXiV][2024] FPT: PEFT for High-resolution Medical Image Classification [paper] [code]
9. [CV][ICLR][2024] Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model [paper] [code]
10. [CV][AAAI][2024] DTL: Disentangled Transfer Learning for Visual Recognition [paper] [code]
11. [Medical][MICCAI][2024] Fine-grained Prompt Tuning: A Parameter and Memory Efficient Transfer Learning Method for High-resolution Medical Image Classification [paper] [code]
12. [CV][ECCV][2024] Parameter-Efficient and Memory-Efficient Tuning for Vision Transformer: A Disentangled Approach [paper] [None] 
13. [CV][ArXiV][2024] CVPT: Cross-Attention help Visual Prompt Tuning adapt visual task [paper] [code]
14. [CV&Point Cloud][ArXiV][2024] Adapter-X: A Novel General Parameter-Efficient Fine-Tuning Framework for Vision [paper] [code]
15. [NLP][ArXiV][2024] MoRe Fine-Tuning with 10x Fewer Parameters [paper] [code]
16. [NLP][ACL][2024] MEFT: Memory-Efficient Fine-Tuning through Sparse Adapter [paper] [code]
17. [NLP][ACL][2024] MELoRA: Mini-Ensemble Low-Rank Adapters for Parameter-Efficient Fine-Tuning [paper] [code]
18. [CV][ArXiV][2024] iConFormer: Dynamic Parameter-Efficient Tuning with Input-Conditioned Adaptation [paper] [None]
19. [Medical][ArXiV][2024] Pre-training Everywhere: Parameter-Efficient Fine-Tuning for Medical Image Analysis via Target Parameter Pre-training [paper] [None]
20. [NLP][ArXiV][2024] Mixture-of-Subspaces in Low-Rank Adaptation [paper] [code]
21. [NLP][ArXiV][2024] LAYERNORM: A KEY COMPONENT IN PARAMETER-EFFICIENT FINE-TUNING [paper] [None]
22. [NLP][ArXiV][2024] See Further for Parameter Efficient Fine-tuning by Standing on the Shoulders of Decomposition [paper] [code] [None]
23. [CV][ECCV Workshop][2024] Down-Sampling Inter-Layer Adapter for Parameter and Computation Efficient Ultra-Fine-Grained Image Recognition [paper] [code]
24. [CV][ArXiV][2024] Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think [paper] [code]
25. [NLP][EMNLP][2024] MaPPER: Multimodal Prior-guided Parameter Efficient Tuning for Referring Expression Comprehension [paper] [None]
26. [CV][ArXiV]][2024] Fine-Tuning is Fine, if Calibrated [paper] [code]
27. [CV][ArXiV][2024] Lessons Learned from a Unifying Empirical Study of Parameter-Efficient Transfer Learning (PETL) in Visual Recognition [paper] [code]
28. [CV][NeurIPS][2024] PACE: marrying generalization in PArameter-efficient fine-tuning with Consistency rEgularization [paper] [code]
29. [NLP][NeurIPS Workshop FITML][2024] Parameter-Efficient Fine-Tuning of State Space Models [paper] [code]
30. [NLP][ArXiV][2024] Visual Perception by Large Language Model’s Weights [paper] [None]
31. [NLP][NeurIPS][2024] HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning [paper] [code]
32. [CV][ArXiV][2024] LoLDU: Low-Rank Adaptation via Lower-Diag-Upper Decomposition for Parameter-Efficient Fine-Tuning [paper] [code]
33. [NLP][ArXiV][2024] Preserving Pre-trained Representation Space: On Effectiveness of Prefix-tuning for Large Multi-modal Models [paper] [None]
34. [NLP][ArXiV][2024] LORA VS FULL FINE-TUNING: AN ILLUSION OF EQUIVALENCE [paper] [None]
35. [NLP][ArXiV][2024] Visual Cue Enhancement and Dual Low-Rank Adaptation for Efficient Visual Instruction Fine-Tuning [paper] [None]
36. [NLP][ArXiV][2024] Separable Mixture of Low-Rank Adaptation for Continual Visual Instruction Tuning [paper] [None]
37. [CV][ArXiV][2024] Enhancing Parameter-Efficient Fine-Tuning of Vision Transformers through Frequency-Based Adaptation [paper] [code]
38. [CV][ArXiV][2024] SimCMF: ASimple Cross-modal Fine-tuning Strategy from Vision Foundation Models to Any Imaging Modality [paper] [code]
39. [CV][icassp][2025] Semantic Hierarchical Prompt Tuning for Parameter-Efficient Fine-Tuning [paper] [code]
40. [Vision&Language][ArXiV][2024] Towards Compatible Fine-tuning for Vision-Language Model [paper] [None]

Year 2023

1. [CV][TCSVT][2023] Pro-tuning: Unified Prompt Tuning for Vision Tasks [paper] [None]
2. [Medical][ArXiV][2023] DVPT: Dynamic Visual Prompt Tuning of Large Pre-trained Models for Medical Image Analysis [paper] [None]
3. [CV][ArXiV][2023] Parameter-efficient is not sufficient: Exploring Parameter, Memory, and Time Efficient Adapter Tuning for Dense Predictions [paper] [None]
4. [CV][ArXiV][2023] PVP: Pre-trained Visual Parameter-Efficient Tuning [paper] [None]
5. [CV][CVPR][2023] Visual Query Tuning: Towards Effective Usage of Intermediate Representations for Parameter and Memory Efficient Transfer Learning [paper] [code]
6. [CV][ICCV][2023] E2VPT: An Effective and Efficient Approach for Visual Prompt Tuning [paper] [code]
7. [CV][ArXiV][2023] PVP: Pre-trained Visual ParameterEfficient Tuning [paper] [None]

Year 2022

1. [CV][ECCV][2022] Visual Prompt Tuning [paper] [code]

Year 2021

Year 2020

Medical Datasets of EFT

Name	Modality	Task	Train	Val	Test	Link
MHIST	Path.	Cls.	3152	-	-	https://bmirds.github.io/MHIST/
Chest X-ray PD	X-ray	Cls.	4575	-	-	COVID19, Pneumonia and Normal Chest X-ray PA Dataset - Mendeley Data
Retinal OCT C8	OCT	Cls.	18400	2800	2800	Retinal OCT - C8 (kaggle.com)
GlaS	Path.	Seg.	85	-	80	https://www.kaggle.com/datasets/sani84/glasmiccai2015-gland-segmentation
QaTa-COVID19-v2	X-ray	Seg.	7145	-	2113	https://www.kaggle.com/datasets/aysendegerli/qatacov19-dataset
ChestXR	X-ray	Cls.	17955	-	3430	https://cxr-covid19.grand-challenge.org/Download/
HAM10000	Skin	Cls.	10015	-	-	https://www.kaggle.com/datasets/kmader/skin-cancer-mnist-ham10000
ISIC2017	Skin	Seg.	2000	150	600	ISIC Challenge (isic-archive.com)
Kvasir-SEG	Endoscope	Seg.	880	120	160	Simula Datasets - Kvasir SEG
CRAG	Path.	Seg.	173		40	https://warwick.ac.uk/fac/cross_fac/tia/data/mildnet/
Messidor-2	Fundus	Cls.	1748			https://www.kaggle.com/datasets/mariaherrerot/messidor2preprocess
BUSI	Ultrasound	Cls./Seg.	780			https://link.zhihu.com/?target=https%3A//scholar.cu.edu.eg/%3Fq%3Dafahmy/pages/dataset
...