Cover Image

MedCutMix: A Data-Centric Approach to Improve Radiology Vision-Language Pre-training with Disease Awareness

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Sinuo, Xie, Yutong, Liu, Yuyuan, Wu, Qi
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-training Framework
by: Phan, Vu Minh Hieu, et al.
Published: (2024)

PairAug: What Can Augmented Image-Text Pairs Do for Radiology?
by: Xie, Yutong, et al.
Published: (2024)

VELVET-Med: Vision and Efficient Language Pre-training for Volumetric Imaging Tasks in Medicine
by: Zhang, Ziyang, et al.
Published: (2025)

UKnow: A Unified Knowledge Protocol with Multimodal Knowledge Graph Datasets for Reasoning and Vision-Language Pre-Training
by: Gong, Biao, et al.
Published: (2023)

Dynamic Cluster Data Sampling for Efficient and Long-Tail-Aware Vision-Language Pre-training
by: Liang, Mingliang, et al.
Published: (2026)

A Reality Check of Vision-Language Pre-training in Radiology: Have We Progressed Using Text?
by: Silva-Rodríguez, Julio, et al.
Published: (2025)

Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image Understanding
by: Shui, Zhongyi, et al.
Published: (2025)

A Survey of Medical Vision-and-Language Applications and Their Techniques
by: Chen, Qi, et al.
Published: (2024)

MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations
by: Zhang, Ziyang, et al.
Published: (2025)

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness
by: Wang, Zeyu, et al.
Published: (2025)

Med-GLIP: Advancing Medical Language-Image Pre-training with Large-scale Grounded Dataset
by: Deng, Ziye, et al.
Published: (2025)

Act Like a Radiologist: Radiology Report Generation across Anatomical Regions
by: Chen, Qi, et al.
Published: (2023)

Unsupervised Pre-training with Language-Vision Prompts for Low-Data Instance Segmentation
by: Zhang, Dingwen, et al.
Published: (2024)

VisionPAD: A Vision-Centric Pre-training Paradigm for Autonomous Driving
by: Zhang, Haiming, et al.
Published: (2024)

A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning
by: Wen, Xin, et al.
Published: (2025)

MMCLIP: Cross-modal Attention Masked Modelling for Medical Language-Image Pre-Training
by: Wu, Biao, et al.
Published: (2024)

Understanding the Multi-modal Prompts of the Pre-trained Vision-Language Model
by: Ma, Shuailei, et al.
Published: (2023)

Scaling Pre-training to One Hundred Billion Data for Vision Language Models
by: Wang, Xiao, et al.
Published: (2025)

MedFILIP: Medical Fine-grained Language-Image Pre-training
by: Liang, Xinjie, et al.
Published: (2025)

3D Scene Graph Guided Vision-Language Pre-training
by: Liu, Hao, et al.
Published: (2024)

TiMix: Text-aware Image Mixing for Effective Vision-Language Pre-training
by: Jiang, Chaoya, et al.
Published: (2023)

Efficient Vision-Language Pre-training by Cluster Masking
by: Wei, Zihao, et al.
Published: (2024)

Enhancing Vision-Language Pre-training with Rich Supervisions
by: Gao, Yuan, et al.
Published: (2024)

Continual Retinal Vision-Language Pre-training upon Incremental Imaging Modalities
by: Yao, Yuang, et al.
Published: (2025)

Intensive Vision-guided Network for Radiology Report Generation
by: Zheng, Fudan, et al.
Published: (2024)

Can Medical Vision-Language Pre-training Succeed with Purely Synthetic Data?
by: Liu, Che, et al.
Published: (2024)

RegionMed-CLIP: A Region-Aware Multimodal Contrastive Learning Pre-trained Model for Medical Image Understanding
by: Fang, Tianchen, et al.
Published: (2025)

Boosting Vision Semantic Density with Anatomy Normality Modeling for Medical Vision-language Pre-training
by: Cao, Weiwei, et al.
Published: (2025)

Multilingual Vision-Language Pre-training for the Remote Sensing Domain
by: Silva, João Daniel, et al.
Published: (2024)

MMCOMPOSITION: Revisiting the Compositionality of Pre-trained Vision-Language Models
by: Hua, Hang, et al.
Published: (2024)

Unsupervised Domain Adaption Harnessing Vision-Language Pre-training
by: Zhou, Wenlve, et al.
Published: (2024)

Data Augmentation in Human-Centric Vision
by: Jiang, Wentao, et al.
Published: (2024)

Omniview-Tuning: Boosting Viewpoint Invariance of Vision-Language Pre-training Models
by: Ruan, Shouwei, et al.
Published: (2024)

TAP-VL: Text Layout-Aware Pre-training for Enriched Vision-Language Models
by: Fhima, Jonathan, et al.
Published: (2024)

RadCLIP: Enhancing Radiologic Image Analysis through Contrastive Language-Image Pre-training
by: Lu, Zhixiu, et al.
Published: (2024)

NoiseCutMix: A Novel Data Augmentation Approach by Mixing Estimated Noise in Diffusion Models
by: Takezaki, Shumpei, et al.
Published: (2025)

Rethinking the Efficiency and Effectiveness of Reinforcement Learning for Radiology Report Generation
by: Lu, Zilin, et al.
Published: (2026)

Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language Models
by: Chen, Mengyuan, et al.
Published: (2024)

Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves
by: Wu, Shihan, et al.
Published: (2024)

Integrating MedCLIP and Cross-Modal Fusion for Automatic Radiology Report Generation
by: Han, Qianhao, et al.
Published: (2024)