English
Related papers

Related papers: Source-Free Domain Adaptive Fundus Image Segmentat…

200 papers

Semi-supervised object detection has made significant progress with the development of mean teacher driven self-training. Despite the promising results, the label mismatch problem is not yet fully explored in the previous works, leading to…

Computer Vision and Pattern Recognition · Computer Science 2022-06-15 Binbin Chen , Weijie Chen , Shicai Yang , Yunyi Xuan , Jie Song , Di Xie , Shiliang Pu , Mingli Song , Yueting Zhuang

Semi-supervised learning reduces the costly manual annotation burden in medical image segmentation. A popular approach is the mean teacher (MT) strategy, which applies consistency regularization using a temporally averaged teacher model. In…

Computer Vision and Pattern Recognition · Computer Science 2025-11-10 Pengchen Zhang , Alan J. X. Guo , Sipin Luo , Zhe Han , Lin Guo

Existing cross-domain keypoint detection methods always require accessing the source data during adaptation, which may violate the data privacy law and pose serious security concerns. Instead, this paper considers a realistic problem…

Computer Vision and Pattern Recognition · Computer Science 2023-02-10 Yuhe Ding , Jian Liang , Bo Jiang , Aihua Zheng , Ran He

Semi-supervised semantic segmentation (SSSS) faces persistent challenges in effectively leveraging unlabeled data, such as ineffective utilization of pseudo-labels, exacerbation of class imbalance biases, and neglect of prediction…

Computer Vision and Pattern Recognition · Computer Science 2025-06-24 Ebenezer Tarubinga , Jenifer Kalafatovich , Seong-Whan Lee

This paper solves a generalized version of the problem of multi-source model adaptation for semantic segmentation. Model adaptation is proposed as a new domain adaptation problem which requires access to a pre-trained model instead of data…

Computer Vision and Pattern Recognition · Computer Science 2022-12-07 Zongyao Li , Ren Togo , Takahiro Ogawa , Miki haseyama

We focus on the source-free domain adaptive object detection (SF-DAOD) problem when source data is unavailable during adaptation and the model must adapt to an unlabeled target domain. The majority of approaches for the problem employ a…

Computer Vision and Pattern Recognition · Computer Science 2025-06-27 Tajamul Ashraf , Janibul Bashir

Effort in releasing large-scale datasets may be compromised by privacy and intellectual property considerations. A feasible alternative is to release pre-trained models instead. While these models are strong on their original task (source…

Computer Vision and Pattern Recognition · Computer Science 2021-05-18 Yunzhong Hou , Liang Zheng

With the rapid advancement of artificial intelligence, intelligent dentistry for clinical diagnosis and treatment has become increasingly promising. As the primary clinical dentistry task, tooth structure segmentation for Cone-Beam Computed…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Muyi Sun , Yifan Gao , Ziang Jia , Xingqun Qi , Qianli Zhang , Qian Liu , Tianzheng Deng

In mixed domain semi-supervised medical image segmentation (MiDSS), achieving superior performance under domain shift and limited annotations is challenging. This scenario presents two primary issues: (1) distributional differences between…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Bentao Song , Jun Huang , Qingfeng Wang

Source-free domain adaptation aims to adapt deep neural networks using only pre-trained source models and target data. However, accessing the source model still has a potential concern about leaking the source data, which reveals the…

Computer Vision and Pattern Recognition · Computer Science 2023-08-24 Shuai Wang , Daoan Zhang , Zipei Yan , Shitong Shao , Rui Li

Medical image annotations are prohibitively time-consuming and expensive to obtain. To alleviate annotation scarcity, many approaches have been developed to efficiently utilize extra information, e.g.,semi-supervised learning further…

Computer Vision and Pattern Recognition · Computer Science 2020-07-14 Kang Li , Shujun Wang , Lequan Yu , Pheng-Ann Heng

Versatile medical image segmentation (VMIS) targets the segmentation of multiple classes, while obtaining full annotations for all classes is often impractical due to the time and labor required. Leveraging partially labeled datasets (PLDs)…

Computer Vision and Pattern Recognition · Computer Science 2025-09-08 Shengqian Zhu , Jiafei Wu , Xiaogang Xu , Chengrong Yu , Ying Song , Zhang Yi , Guangjun Li , Junjie Hu

Point cloud-based medical registration promises increased computational efficiency, robustness to intensity shifts, and anonymity preservation but is limited by the inefficacy of unsupervised learning with similarity metrics. Supervised…

Computer Vision and Pattern Recognition · Computer Science 2023-07-06 Alexander Bigalke , Mattias P. Heinrich

The success of deep convolutional neural networks (DCNNs) benefits from high volumes of annotated data. However, annotating medical images is laborious, expensive, and requires human expertise, which induces the label scarcity problem.…

Image and Video Processing · Electrical Eng. & Systems 2022-03-24 Ziyuan Zhao , Kaixin Xu , Shumeng Li , Zeng Zeng , Cuntai Guan

Pseudo-label (PL) filtering forms a crucial part of Self-Training (ST) methods for unsupervised domain adaptation. Dropout-based Uncertainty-driven Self-Training (DUST) proceeds by first training a teacher model on source domain labeled…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-16 Nauman Dawalatabad , Sameer Khurana , Antoine Laurent , James Glass

Self-training has shown great potential in semi-supervised learning. Its core idea is to use the model learned on labeled data to generate pseudo-labels for unlabeled samples, and in turn teach itself. To obtain valid supervision, active…

Computer Vision and Pattern Recognition · Computer Science 2022-09-20 Ye Du , Yujun Shen , Haochen Wang , Jingjing Fei , Wei Li , Liwei Wu , Rui Zhao , Zehua Fu , Qingjie Liu

Existing cross-domain few-shot learning (CDFSL) methods, which develop source-domain training strategies to enhance model transferability, face challenges with large-scale pre-trained models (LMs) due to inaccessible source data and…

Computer Vision and Pattern Recognition · Computer Science 2025-09-16 Huali Xu , Li Liu , Tianpeng Liu , Shuaifeng Zhi , Shuzhou Sun , Ming-Ming Cheng

In semi-supervised domain adaptation, a few labeled samples per class in the target domain guide features of the remaining target samples to aggregate around them. However, the trained model cannot produce a highly discriminative feature…

Computer Vision and Pattern Recognition · Computer Science 2021-04-20 Jichang Li , Guanbin Li , Yemin Shi , Yizhou Yu

The standard closed-set domain adaptation approaches seek to mitigate distribution discrepancies between two domains under the constraint of both sharing identical label sets. However, in realistic scenarios, finding an optimal source…

Machine Learning · Computer Science 2022-12-06 Sandipan Choudhuri , Suli Adeniye , Arunabha Sen , Hemanth Venkateswara

Recent deep networks achieved state of the art performance on a variety of semantic segmentation tasks. Despite such progress, these models often face challenges in real world `wild tasks' where large difference between labeled…

Computer Vision and Pattern Recognition · Computer Science 2018-10-26 Yang Zou , Zhiding Yu , B. V. K. Vijaya Kumar , Jinsong Wang