3 citations · 4 across the 9 of their papers we have counts for
6 papers · 1 filter
Domain Adaptive Diabetic Retinopathy Grading with Model Absence and Flowing Data
Wenxin Su, Song Tang, Xiaofeng Liu +5
Domain shift (the difference between source and target domains) poses a significant challenge in clinical applications, e.g., Diabetic Retinopathy (DR) grading. Despite considering…
Prototypical Few-Shot Medical Image Semantic Segmentation with Background Fusion
Yuan Dong, Xiaoyu Yu, Wentao Wan +4
Few-shot Semantic Segmentation (FSS) aims to adapt a pre-trained model to new classes with as few as a single labeled training sample per class. The existing prototypical work used…
Source-Free Domain Adaptive Object Detection with Semantics Compensation
Song Tang, Jiuzheng Yang, Mao Ye +3
Strong data augmentation is a fundamental component of state-of-the-art mean teacher-based Source-Free domain adaptive Object Detection (SFOD) methods, enabling consistency-based s…
Few-Shot Medical Image Segmentation with High-Fidelity Prototypes
Song Tang, Shaxu Yan, Xiaozhi Qi +4
Few-shot Semantic Segmentation (FSS) aims to adapt a pretrained model to new classes with as few as a single labelled training sample per class. Despite the prototype based approac…
Proxy Denoising for Source-Free Domain Adaptation
Song Tang, Wenxin Su, Yan Gan +3
Source-Free Domain Adaptation (SFDA) aims to adapt a pre-trained source model to an unlabeled target domain with no access to the source data. Inspired by the success of large Visi…
Unified Source-Free Domain Adaptation
Song Tang, Wenxin Su, Mao Ye +2
In the pursuit of transferring a source model to a target domain without access to the source training data, Source-Free Domain Adaptation (SFDA) has been extensively explored acro…