中文
相关论文

相关论文: Improving Pseudo Labels With Intra-Class Similarit…

200 篇论文

Self-training based on pseudo-labels has emerged as a dominant approach for addressing conditional distribution shifts in unsupervised domain adaptation (UDA) for semantic segmentation problems. A notable drawback, however, is that this…

计算机视觉与模式识别 · 计算机科学 2023-05-02 Rajshekhar Das , Jonathan Francis , Sanket Vaibhav Mehta , Jean Oh , Emma Strubell , Jose Moura

Unsupervised Domain Adaptation (UDA) aims to adapt models trained on a source domain to a new target domain where no labelled data is available. In this work, we investigate the problem of UDA from a synthetic computer-generated domain to a…

计算机视觉与模式识别 · 计算机科学 2021-11-29 Stephan Brehm , Sebastian Scherer , Rainer Lienhart

Most existing studies on unsupervised domain adaptation (UDA) assume that each domain's training samples come with domain labels (e.g., painting, photo). Samples from each domain are assumed to follow the same distribution and the domain…

计算机视觉与模式识别 · 计算机科学 2022-07-27 Zhongying Deng , Kaiyang Zhou , Da Li , Junjun He , Yi-Zhe Song , Tao Xiang

Unsupervised Domain Adaptation (UDA) approaches address the covariate shift problem by minimizing the distribution discrepancy between the source and target domains, assuming that the label distribution is invariant across domains. However,…

机器学习 · 计算机科学 2023-08-22 Xiaona Sun , Zhenyu Wu , Yichen Liu , Saier Hu , Zhiqiang Zhan , Yang Ji

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…

计算机视觉与模式识别 · 计算机科学 2021-04-20 Jichang Li , Guanbin Li , Yemin Shi , Yizhou Yu

Unsupervised domain adaptation (UDA) methods intend to reduce the gap between source and target domains by using unlabeled target domain and labeled source domain data, however, in the medical domain, target domain data may not always be…

图像与视频处理 · 电气工程与系统科学 2022-02-01 Mingxuan Gu , Sulaiman Vesal , Ronak Kosti , Andreas Maier

Semi-Supervised Domain Adaptation (SSDA) involves learning to classify unseen target data with a few labeled and lots of unlabeled target data, along with many labeled source data from a related domain. Current SSDA approaches usually aim…

计算机视觉与模式识别 · 计算机科学 2023-03-28 Yu-Chu Yu , Hsuan-Tien Lin

Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset, making it applicable in a variety of real-world scenarios. Existing SFDA methods ONLY assess…

计算机视觉与模式识别 · 计算机科学 2023-10-10 Longxiang Tang , Kai Li , Chunming He , Yulun Zhang , Xiu Li

Many variants of unsupervised domain adaptation (UDA) problems have been proposed and solved individually. Its side effect is that a method that works for one variant is often ineffective for or not even applicable to another, which has…

计算机视觉与模式识别 · 计算机科学 2021-06-04 Yu Mitsuzumi , Go Irie , Daiki Ikami , Takashi Shibata

Recent advancements in deep learning-based wearable human action recognition (wHAR) have improved the capture and classification of complex motions, but adoption remains limited due to the lack of expert annotations and domain discrepancies…

计算机视觉与模式识别 · 计算机科学 2024-10-24 Indrajeet Ghosh , Garvit Chugh , Abu Zaher Md Faridee , Nirmalya Roy

Unsupervised open-set domain adaptation (UODA) is a realistic problem where unlabeled target data contain unknown classes. Prior methods rely on the coexistence of both source and target domain data to perform domain alignment, which…

计算机视觉与模式识别 · 计算机科学 2021-09-08 Zeyu Feng , Chang Xu , Dacheng Tao

Semi-supervised domain adaptation (SSDA) adapts a learner to a new domain by effectively utilizing source domain data and a few labeled target samples. It is a practical yet under-investigated research topic. In this paper, we analyze the…

计算机视觉与模式识别 · 计算机科学 2023-03-31 Wenqiao Zhang , Changshuo Liu , Can Cui , Beng Chin Ooi

The primary objective of domain adaptation methods is to transfer knowledge from a source domain to a target domain that has similar but different data distributions. Thus, in order to correctly classify the unlabeled target domain samples,…

机器学习 · 计算机科学 2019-08-12 Rohith AP , Ambedkar Dukkipati , Gaurav Pandey

Domain Adaptation (DA) is important for deep learning-based medical image segmentation models to deal with testing images from a new target domain. As the source-domain data are usually unavailable when a trained model is deployed at a new…

计算机视觉与模式识别 · 计算机科学 2023-11-22 Jianghao Wu , Guotai Wang , Ran Gu , Tao Lu , Yinan Chen , Wentao Zhu , Tom Vercauteren , Sébastien Ourselin , Shaoting Zhang

Self-supervised learning approaches for unsupervised domain adaptation (UDA) of semantic segmentation models suffer from challenges of predicting and selecting reasonable good quality pseudo labels. In this paper, we propose a novel…

计算机视觉与模式识别 · 计算机科学 2020-07-30 M. Naseer Subhani , Mohsen Ali

Many unsupervised domain adaptive (UDA) person re-identification (ReID) approaches combine clustering-based pseudo-label prediction with feature fine-tuning. However, because of domain gap, the pseudo-labels are not always reliable and…

计算机视觉与模式识别 · 计算机科学 2020-12-18 Kecheng Zheng , Cuiling Lan , Wenjun Zeng , Zhizheng Zhang , Zheng-Jun Zha

Unsupervised Domain Adaptation (UDA) for point cloud classification is an emerging research problem with relevant practical motivations. Reliance on multi-task learning to align features across domains has been the standard way to tackle…

计算机视觉与模式识别 · 计算机科学 2021-10-22 Adriano Cardace , Riccardo Spezialetti , Pierluigi Zama Ramirez , Samuele Salti , Luigi Di Stefano

Most unsupervised domain adaptation (UDA) methods assume that labeled source images are available during model adaptation. However, this assumption is often infeasible owing to confidentiality issues or memory constraints on mobile devices.…

计算机视觉与模式识别 · 计算机科学 2023-03-17 JoonHo Lee , Gyemin Lee

We address the Unsupervised Domain Adaptation (UDA) problem in image classification from a new perspective. In contrast to most existing works which either align the data distributions or learn domain-invariant features, we directly learn a…

计算机视觉与模式识别 · 计算机科学 2020-12-03 Qian Wang , Fanlin Meng , Toby P. Breckon

Unsupervised domain adaptation (UDA) involves adapting a model trained on a label-rich source domain to an unlabeled target domain. However, in real-world scenarios, the absence of target-domain labels makes it challenging to evaluate the…

计算机视觉与模式识别 · 计算机科学 2024-02-20 Jianfei Yang , Hanjie Qian , Yuecong Xu , Kai Wang , Lihua Xie