Copertina

More performant and scalable: Rethinking contrastive vision-language pre-training of radiology in the LLM era

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Yingtai, Lai, Haoran, Zhou, Xiaoqian, Ming, Shuai, Ma, Wenxin, Wei, Wei, Zhou, Shaohua Kevin
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

GreenRFM: Toward a resource-efficient radiology foundation model
di: Li, Yingtai, et al.
Pubblicazione: (2026)

ASAP: Advancing Medical Volumetric Representation Learning with Anatomy-aware Semantically-adaptive Pre-training
di: Wang, Rongsheng, et al.
Pubblicazione: (2026)

DiffVP: Differential Visual Semantic Prompting for LLM-Based CT Report Generation
di: Tian, Yuhe, et al.
Pubblicazione: (2026)

MedReason-R1: Learning to Reason for CT Diagnosis with Reinforcement Learning and Local Zoom
di: Li, Yifan, et al.
Pubblicazione: (2025)

Concept-to-Pixel: Prompt-Free Universal Medical Image Segmentation
di: Chen, Haoyun, et al.
Pubblicazione: (2026)

MambaMIM: Pre-training Mamba with State Space Token Interpolation and its Application to Medical Image Segmentation
di: Tang, Fenghe, et al.
Pubblicazione: (2024)

DeViDe: Faceted medical knowledge for improved medical vision-language pre-training
di: Luo, Haozhe, et al.
Pubblicazione: (2024)

Expert-level vision-language foundation model for real-world radiology and comprehensive evaluation
di: Liu, Xiaohong, et al.
Pubblicazione: (2024)

Med3D-R1: Incentivizing Clinical Reasoning in 3D Medical Vision-Language Models for Abnormality Diagnosis
di: Lai, Haoran, et al.
Pubblicazione: (2026)

AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP
di: Ma, Wenxin, et al.
Pubblicazione: (2025)

Hi-End-MAE: Hierarchical encoder-driven masked autoencoders are stronger vision learners for medical image segmentation
di: Tang, Fenghe, et al.
Pubblicazione: (2025)

SimCroP: Radiograph Representation Learning with Similarity-driven Cross-granularity Pre-training
di: Wang, Rongsheng, et al.
Pubblicazione: (2025)

OmDet: Large-scale vision-language multi-dataset pre-training with multimodal detection network
di: Zhao, Tiancheng, et al.
Pubblicazione: (2022)

ECAMP: Entity-centered Context-aware Medical Vision Language Pre-training
di: Wang, Rongsheng, et al.
Pubblicazione: (2023)

Pre-Trained LLM is a Semantic-Aware and Generalizable Segmentation Booster
di: Tang, Fenghe, et al.
Pubblicazione: (2025)

Enhancing medical vision-language contrastive learning via inter-matching relation modelling
di: Li, Mingjian, et al.
Pubblicazione: (2024)

From pre-training to downstream performance: Does domain-specific pre-training make sense?
di: Krones, Felix
Pubblicazione: (2026)

Hyperlocal disaster damage assessment using bi-temporal street-view imagery and pre-trained vision models
di: Yang, Yifan, et al.
Pubblicazione: (2025)

3DGR-CT: Sparse-View CT Reconstruction with a 3D Gaussian Representation
di: Li, Yingtai, et al.
Pubblicazione: (2023)

When are radiology reports useful for training medical image classifiers?
di: Bergström, Herman, et al.
Pubblicazione: (2025)

UCAD: Uncertainty-guided Contour-aware Displacement for semi-supervised medical image segmentation
di: Ding, Chengbo, et al.
Pubblicazione: (2026)

QCAgent: An agentic framework for quality-controllable pathology report generation from whole slide image
di: Wang, Rundong, et al.
Pubblicazione: (2026)

Landmarks Are Alike Yet Distinct: Harnessing Similarity and Individuality for One-Shot Medical Landmark Detection
di: He, Xu, et al.
Pubblicazione: (2025)

HYATT-Net is Grand: A Hybrid Attention Network for Performant Anatomical Landmark Detection
di: Zhou, Xiaoqian, et al.
Pubblicazione: (2024)

Hallucination-aware intermediate representation edit in large vision-language models
di: Suo, Wei, et al.
Pubblicazione: (2026)

Bridged Semantic Alignment for Zero-shot 3D Medical Image Diagnosis
di: Lai, Haoran, et al.
Pubblicazione: (2025)

MedAtlas: Evaluating LLMs for Multi-Round, Multi-Task Medical Reasoning Across Diverse Imaging Modalities and Clinical Text
di: Xu, Ronghao, et al.
Pubblicazione: (2025)

Comprehensive language-image pre-training for 3D medical image understanding
di: Wald, Tassilo, et al.
Pubblicazione: (2025)

Bridging vision language model (VLM) evaluation gaps with a framework for scalable and cost-effective benchmark generation
di: Rädsch, Tim, et al.
Pubblicazione: (2025)

U-Bench: A Comprehensive Understanding of U-Net through 100-Variant Benchmarking
di: Tang, Fenghe, et al.
Pubblicazione: (2025)

FFF: Fixing Flawed Foundations in contrastive pre-training results in very strong Vision-Language models
di: Bulat, Adrian, et al.
Pubblicazione: (2024)

MGI: Multimodal Contrastive pre-training of Genomic and Medical Imaging
di: Zhou, Jiaying, et al.
Pubblicazione: (2024)

3DGR-CAR: Coronary artery reconstruction from ultra-sparse 2D X-ray views with a 3D Gaussians representation
di: Fu, Xueming, et al.
Pubblicazione: (2024)

Towards Accurate Unified Anomaly Segmentation
di: Ma, Wenxin, et al.
Pubblicazione: (2025)

No Re-Train, More Gain: Upgrading Backbones with Diffusion model for Pixel-Wise and Weakly-Supervised Few-Shot Segmentation
di: Chen, Shuai, et al.
Pubblicazione: (2024)

BUS:Efficient and Effective Vision-language Pre-training with Bottom-Up Patch Summarization
di: Jiang, Chaoya, et al.
Pubblicazione: (2023)

A General Knowledge Injection Framework for ICD Coding
di: Zhang, Xu, et al.
Pubblicazione: (2025)

Increasing the scalability of graph convolution for FPGA-implemented event-based vision
di: Wzorek, Piotr, et al.
Pubblicazione: (2024)

Rethinking Dual-Domain Undersampled MRI reconstruction: domain-specific design from the perspective of the receptive field
di: Gao, Ziqi, et al.
Pubblicazione: (2023)

SDPT: Synchronous Dual Prompt Tuning for Fusion-based Visual-Language Pre-trained Models
di: Zhou, Yang, et al.
Pubblicazione: (2024)