Cover Image

Deep Expert Injection for Anchoring Retinal VLMs with Domain-Specific Knowledge

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lu, Shuai, Wang, Meng, Guo, Jia, Du, Jiawei, Liu, Bo, Yang, Shengzhu, Zhang, Weihang, Fu, Huazhu, Li, Huiqi
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ViLReF: An Expert Knowledge Enabled Vision-Language Retinal Foundation Model
by: Yang, Shengzhu, et al.
Published: (2024)

RET-CLIP: A Retinal Image Foundation Model Pre-trained with Clinical Diagnostic Reports
by: Du, Jiawei, et al.
Published: (2024)

CLIPin: A Non-contrastive Plug-in to CLIP for Multimodal Semantic Alignment
by: Yang, Shengzhu, et al.
Published: (2025)

Absolute-Unified Multi-Class Anomaly Detection via Class-Agnostic Distribution Alignment
by: Guo, Jia, et al.
Published: (2024)

Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection
by: Guo, Jia, et al.
Published: (2024)

Native Intelligence Emerges from Large-Scale Clinical Practice: A Retinal Foundation Model with Deployment Efficiency
by: Guo, Jia, et al.
Published: (2025)

MM-Retinal: Knowledge-Enhanced Foundational Pretraining with Fundus Image-Text Expertise
by: Wu, Ruiqi, et al.
Published: (2024)

Unsupervised Domain Adaptation via Style-Aware Self-intermediate Domain
by: Wang, Lianyu, et al.
Published: (2022)

One Dinomaly2 Detect Them All: A Unified Framework for Full-Spectrum Unsupervised Anomaly Detection
by: Guo, Jia, et al.
Published: (2025)

Reliable Joint Segmentation of Retinal Edema Lesions in OCT Images
by: Wang, Meng, et al.
Published: (2022)

MM-Retinal V2: Transfer an Elite Knowledge Spark into Fundus Vision-Language Pretraining
by: Wu, Ruiqi, et al.
Published: (2025)

Chimera: Improving Generalist Model with Domain-Specific Experts
by: Peng, Tianshuo, et al.
Published: (2024)

Deep Pre-Alignment for VLMs
by: Yu, Tianyu, et al.
Published: (2026)

Serp-Mamba: Advancing High-Resolution Retinal Vessel Segmentation with Selective State-Space Model
by: Wang, Hongqiu, et al.
Published: (2024)

Exploring the Effectiveness of Deep Features from Domain-Specific Foundation Models in Retinal Image Synthesis
by: Skorniewska, Zuzanna, et al.
Published: (2025)

Vision-Language Model IP Protection via Prompt-based Learning
by: Wang, Lianyu, et al.
Published: (2025)

MExD: An Expert-Infused Diffusion Model for Whole-Slide Image Classification
by: Zhao, Jianwei, et al.
Published: (2025)

SMoES: Soft Modality-Guided Expert Specialization in MoE-VLMs
by: Bo, Zi-Hao, et al.
Published: (2026)

KALAHash: Knowledge-Anchored Low-Resource Adaptation for Deep Hashing
by: Zhao, Shu, et al.
Published: (2024)

Virtual Classification: Modulating Domain-Specific Knowledge for Multidomain Crowd Counting
by: Guo, Mingyue, et al.
Published: (2024)

UHR-Micro: Diagnosing and Mitigating the Resolution Illusion in Earth Observation VLMs
by: Ni, Shuo, et al.
Published: (2026)

Distilling Expert Surgical Knowledge: How to train local surgical VLMs for anatomy explanation in Complete Mesocolic Excision
by: Maack, Lennart, et al.
Published: (2025)

MyVLM: Personalizing VLMs for User-Specific Queries
by: Alaluf, Yuval, et al.
Published: (2024)

Enhancing Medical Visual Grounding via Knowledge-guided Spatial Prompts
by: Gao, Yifan, et al.
Published: (2026)

Boosting the Generalization Ability for Hyperspectral Image Classification using Spectral-spatial Axial Aggregation Transformer
by: Zhao, Enzhe, et al.
Published: (2023)

Sparse Spectral LoRA: Routed Experts for Medical VLMs
by: Manzari, Omid Nejati, et al.
Published: (2026)

Deepfake Detection via Knowledge Injection
by: Li, Tonghui, et al.
Published: (2025)

VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection
by: Cheng, Hao, et al.
Published: (2025)

Teaching VLMs to Localize Specific Objects from In-context Examples
by: Doveh, Sivan, et al.
Published: (2024)

Beyond the Eye: A Relational Model for Early Dementia Detection Using Retinal OCTA Images
by: Liu, Shouyue, et al.
Published: (2024)

CLIP-DR: Textual Knowledge-Guided Diabetic Retinopathy Grading with Ranking-aware Prompting
by: Yu, Qinkai, et al.
Published: (2024)

MX-Font++: Mixture of Heterogeneous Aggregation Experts for Few-shot Font Generation
by: Wang, Weihang, et al.
Published: (2025)

Adversarial Transferability in Deep Denoising Models: Theoretical Insights and Robustness Enhancement via Out-of-Distribution Typical Set Sampling
by: Ning, Jie, et al.
Published: (2024)

Reliable Source Approximation: Source-Free Unsupervised Domain Adaptation for Vestibular Schwannoma MRI Segmentation
by: Zeng, Hongye, et al.
Published: (2024)

VLMs have Tunnel Vision: Evaluating Nonlocal Visual Reasoning in Leading VLMs
by: Berman, Shmuel, et al.
Published: (2025)

AIF-SFDA: Autonomous Information Filter-driven Source-Free Domain Adaptation for Medical Image Segmentation
by: Li, Haojin, et al.
Published: (2025)

Convolutional Prompting for Broad-Domain Retinal Vessel Segmentation
by: Wei, Qijie, et al.
Published: (2024)

Learnable Prompting SAM-induced Knowledge Distillation for Semi-supervised Medical Image Segmentation
by: Huang, Kaiwen, et al.
Published: (2024)

Re-initialization-free Level Set Method via Molecular Beam Epitaxy Equation Regularization for Image Segmentation
by: Song, Fanghui, et al.
Published: (2023)

SILSM: A Sustainable Interactive Level Set Method for Progressive Refinement
by: Song, Jiachen, et al.
Published: (2026)