173 citations · 256 across the 28 of their papers we have counts for
14 papers · 1 filter
Text to Image for Multi-Label Image Recognition with Joint Prompt-Adapter Learning
Chun-Mei Feng, Kai Yu, Xinxing Xu +4
Benefited from image-text contrastive learning, pre-trained vision-language models, e.g., CLIP, allow to direct leverage texts as images (TaI) for parameter-efficient fine-tuning (…
Partially Supervised Unpaired Multi-Modal Learning for Label-Efficient Medical Image Segmentation
Lei Zhu, Yanyu Xu, Huazhu Fu +3
Unpaired Multi-Modal Learning (UMML) which leverages unpaired multi-modal data to boost model performance on each individual modality has attracted a lot of research interests in m…
BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays
Yang Zhou, Tan Li Hui Faith, Yanyu Xu +4
Medical Vision-Language Pretraining (MedVLP) shows promise in learning generalizable and transferable visual representations from paired and unpaired medical images and reports. Me…
UrFound: Towards Universal Retinal Foundation Models via Knowledge-Guided Masked Modeling
Kai Yu, Yang Zhou, Yang Bai +5
Retinal foundation models aim to learn generalizable representations from diverse retinal images, facilitating label-efficient model adaptation across various ophthalmic tasks. Des…
Clinical Domain Knowledge-Derived Template Improves Post Hoc AI Explanations in Pneumothorax Classification
Han Yuan, Chuan Hong, Pengtao Jiang +5
Background: Pneumothorax is an acute thoracic disease caused by abnormal air collection between the lungs and chest wall. To address the opaqueness often associated with deep learn…
Learning Prompt with Distribution-Based Feature Replay for Few-Shot Class-Incremental Learning
Zitong Huang, Ze Chen, Zhixing Chen +6
Few-shot Class-Incremental Learning (FSCIL) aims to continuously learn new classes based on very limited training data without forgetting the old ones encountered. Existing studies…
VQA4CIR: Boosting Composed Image Retrieval with Visual Question Answering
Chun-Mei Feng, Yang Bai, Tao Luo +6
Albeit progress has been made in Composed Image Retrieval (CIR), we empirically find that a certain percentage of failure retrieval results are not consistent with their relative c…
Sentence-level Prompts Benefit Composed Image Retrieval
Yang Bai, Xinxing Xu, Yong Liu +5
Composed image retrieval (CIR) is the task of retrieving specific images by using a query that involves both a reference image and a relative caption. Most existing CIR models adop…
Learning Federated Visual Prompt in Null Space for MRI Reconstruction
Chun-Mei Feng, Bangjun Li, Xinxing Xu +3
Federated Magnetic Resonance Imaging (MRI) reconstruction enables multiple hospitals to collaborate distributedly without aggregating local data, thereby protecting patient privacy…
Medical Phrase Grounding with Region-Phrase Context Contrastive Alignment
Zhihao Chen, Yang Zhou, Anh Tran +8
Medical phrase grounding (MPG) aims to locate the most relevant region in a medical image, given a phrase query describing certain medical findings, which is an important task for…
Reliable Federated Disentangling Network for Non-IID Domain Feature
Meng Wang, Kai Yu, Chun-Mei Feng +6
Federated learning (FL), as an effective decentralized distributed learning approach, enables multiple institutions to jointly train a model without sharing their local data. Howev…
CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow
Xiuchao Sui, Shaohua Li, Xue Geng +5
Optical flow estimation aims to find the 2D motion field by identifying corresponding pixels between two images. Despite the tremendous progress of deep learning-based optical flow…
GAMMA Challenge:Glaucoma grAding from Multi-Modality imAges
Junde Wu, Huihui Fang, Fei Li +26
Color fundus photography and Optical Coherence Tomography (OCT) are the two most cost-effective tools for glaucoma screening. Both two modalities of images have prominent biomarker…
Few-Shot Domain Adaptation with Polymorphic Transformers
Shaohua Li, Xiuchao Sui, Jie Fu +7
Deep neural networks (DNNs) trained on one set of medical images often experience severe performance drop on unseen test images, due to various domain discrepancy between the train…