Guardado en:
Detalles Bibliográficos
Autores principales: Cui, Xiangxiang, Huang, Tianjin, Wang, Yifang, Hu, Lijie, Yin, Lu
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2605.19027
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917525942435840
author Cui, Xiangxiang
Huang, Tianjin
Wang, Yifang
Hu, Lijie
Yin, Lu
author_facet Cui, Xiangxiang
Huang, Tianjin
Wang, Yifang
Hu, Lijie
Yin, Lu
contents Medical foundation models have achieved remarkable clinical performance, yet their robustness under real-world perturbations remains underexplored. We present a robustness benchmark comprising 40 perturbation types (12 base, 28 medical-specific) across eight imaging modalities, evaluating five VLMs (LLaVA-Med, MedGemma, MedGemma-1.5, Gemini-2.5-flash and GPT-4o-mini) on VQA, visual grounding, and captioning, alongside two segmentation models (MedSAM, SAM-Med2D) with five fine-tuning strategies. Our findings reveal: (1) Fine-tuning strategy dominates robustness, with LoRA exhibiting nearly double the degradation of full fine-tuning, while SAM-Med2D's Adapter offers favorable efficiency-robustness trade-off. (2) Medical-specific perturbations disproportionately damage segmentation, with 9 of 15 top corruptions being domain-specific. (3) LoRA-tuned visual grounding drops over 40 points, whereas zero-shot captioning remains stable (<7% drop). Zero-shot VQA shows model-dependent robustness--medical models drop under 20% while Gemini-2.5-flash drops 54%. General-purpose VLMs achieve higher VQA accuracy but fail on grounding; among medical VLMs, MedGemma demonstrates the best overall stability. These results provide deployment guidelines and underscore the necessity of domain-specific robustness evaluation for medical AI. Our code is available at: https://abnerai.github.io/MedFM-Robust.
format Preprint
id arxiv_https___arxiv_org_abs_2605_19027
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MedFM-Robust: Benchmarking Robustness of Medical Foundation Models
Cui, Xiangxiang
Huang, Tianjin
Wang, Yifang
Hu, Lijie
Yin, Lu
Computer Vision and Pattern Recognition
Medical foundation models have achieved remarkable clinical performance, yet their robustness under real-world perturbations remains underexplored. We present a robustness benchmark comprising 40 perturbation types (12 base, 28 medical-specific) across eight imaging modalities, evaluating five VLMs (LLaVA-Med, MedGemma, MedGemma-1.5, Gemini-2.5-flash and GPT-4o-mini) on VQA, visual grounding, and captioning, alongside two segmentation models (MedSAM, SAM-Med2D) with five fine-tuning strategies. Our findings reveal: (1) Fine-tuning strategy dominates robustness, with LoRA exhibiting nearly double the degradation of full fine-tuning, while SAM-Med2D's Adapter offers favorable efficiency-robustness trade-off. (2) Medical-specific perturbations disproportionately damage segmentation, with 9 of 15 top corruptions being domain-specific. (3) LoRA-tuned visual grounding drops over 40 points, whereas zero-shot captioning remains stable (<7% drop). Zero-shot VQA shows model-dependent robustness--medical models drop under 20% while Gemini-2.5-flash drops 54%. General-purpose VLMs achieve higher VQA accuracy but fail on grounding; among medical VLMs, MedGemma demonstrates the best overall stability. These results provide deployment guidelines and underscore the necessity of domain-specific robustness evaluation for medical AI. Our code is available at: https://abnerai.github.io/MedFM-Robust.
title MedFM-Robust: Benchmarking Robustness of Medical Foundation Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.19027