paper-with-me

Papers

PeFoMed: Parameter Efficient Fine-tuning of Multimodal Large Language Models for Medical Imaging

2024-01-05 · Jinlong He, Pengfei Li, Gang Liu, Genrong He, Zhaolin Chen, Shenjun Zhong

Multimodal large language models (MLLMs) represent an evolutionary expansion in the capabilities of traditional large language models, enabling them to tackle challenges that surpass the scope of purely text-based applications. It leverages the knowledge previously encoded within these language models, thereby enhancing their applicability and functionality in the reign of multimodal contexts. Recent works investigate the adaptation of MLLMs as a universal solution to address medical multi-modal problems as a generative task. In this paper, we propose a parameter efficient framework for fine-tuning MLLMs, specifically validated on medical visual question answering (Med-VQA) and medical report generation (MRG) tasks, using public benchmark datasets. We also introduce an evaluation metric using the 5-point Likert scale and its weighted average value to measure the quality of the generated reports for MRG tasks, where the scale ratings are labelled by both humans manually and the GPT-4 model. We further assess the consistency of performance metrics across traditional measures, GPT-4, and human ratings for both VQA and MRG tasks. The results indicate that semantic similarity assessments using GPT-4 align closely with human annotators and provide greater stability, yet they reveal a discrepancy when compared to conventional lexical similarity measurements. This questions the reliability of lexical similarity metrics for evaluating the performance of generative models in Med-VQA and report generation tasks. Besides, our fine-tuned model significantly outperforms GPT-4v. This indicates that without additional fine-tuning, multi-modal models like GPT-4v do not perform effectively on medical imaging tasks. The code will be available here: https://github.com/jinlHe/PeFoMed.

📄 PDF Abstract BibTeX arXiv:2401.02797

Code (1)

jinlhe/pefomed 공식 구현 pytorch

Tasks

Medical Report GenerationMedical Visual Question Answeringparameter-efficient fine-tuningQuestion AnsweringSemantic SimilaritySemantic Textual SimilarityVisual Question AnsweringVisual Question Answering (VQA)

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Adam 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

Re-Imagining Multimodal Instruction Tuning: A Representation View

2025-03-02 · Yiyang Liu, James Chenhao Liang, Ruixiang Tang, Yugyung Lee 외

Multimodal instruction tuning has proven to be an effective strategy for achieving zero-shot generalization by fine-tuning pre-trained Large Multimodal Models (LMMs) with instruction-following data. However, as the scale…

Instruction FollowingMMEparameter-efficient fine-tuningZero-shot Generalization

An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models

2024-06-07 · Xiongtao Zhou, Jie He, Yuhua Ke, Guangyao Zhu 외

Multimodal large language models (MLLMs) fine-tuned with multimodal instruction datasets have demonstrated remarkable capabilities in multimodal tasks. However, fine-tuning all parameters of MLLMs has become challenging …

Hallucinationparameter-efficient fine-tuning

M$^2$PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning

2024-09-24 · Taowen Wang, Yiyang Liu, James Chenhao Liang, Junhan Zhao 외

Multimodal Large Language Models (MLLMs) demonstrate remarkable performance across a wide range of domains, with increasing emphasis on enhancing their zero-shot generalization capabilities for unseen tasks across variou…

Zero-shot Generalization

Multimodal Instruction Tuning with Conditional Mixture of LoRA

2024-02-24 · Ying Shen, Zhiyang Xu, Qifan Wang, Yu Cheng 외

Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in diverse tasks across different domains, with an increasing focus on improving their zero-shot generalization capabilities for unseen mu…

parameter-efficient fine-tuningZero-shot Generalization

Explore How to Inject Beneficial Noise in MLLMs

2025-11-17 · Ruishu Zhu, Sida Huang, Ziheng Jiao, Hongyuan Zhang arxiv

Multimodal Large Language Models (MLLMs) have played an increasingly important role in multimodal intelligence. However, the existing fine-tuning methods often ignore cross-modal heterogeneity, limiting their full potent…