中文
相关论文

相关论文: Self-Adaptive Partial Domain Adaptation

200 篇论文

A domain (distribution) shift between training and test data often hinders the real-world performance of deep neural networks, necessitating unsupervised domain adaptation (UDA) to bridge this gap. Online source-free UDA has emerged as a…

机器学习 · 计算机科学 2025-06-02 Pascal Schlachter , Jonathan Fuss , Bin Yang

For a target task where labeled data is unavailable, domain adaptation can transfer a learner from a different source domain. Previous deep domain adaptation methods mainly learn a global domain shift, i.e., align the global source and…

计算机视觉与模式识别 · 计算机科学 2021-06-18 Yongchun Zhu , Fuzhen Zhuang , Jindong Wang , Guolin Ke , Jingwu Chen , Jiang Bian , Hui Xiong , Qing He

Domain adaptation (DA) aims to enable a learning model trained from a source domain to generalize well on a target domain, despite the mismatch of data distributions between the two domains. State-of-the-art DA methods have so far focused…

计算机视觉与模式识别 · 计算机科学 2021-01-13 Lingkun Luo , Liming Chen , Shiqiang Hu

As the volume of data continues to expand, it becomes increasingly common for data to be aggregated from multiple sources. Leveraging multiple sources for model training typically achieves better predictive performance on test datasets.…

统计方法学 · 统计学 2025-03-05 Congbin Xu , Chengde Qian , Zhaojun Wang , Changliang Zou

Distribution shifts are all too common in real-world applications of machine learning. Domain adaptation (DA) aims to address this by providing various frameworks for adapting models to the deployment data without using labels. However, the…

机器学习 · 计算机科学 2023-09-08 Linus Ericsson , Da Li , Timothy M. Hospedales

By leveraging data from a fully labeled source domain, unsupervised domain adaptation (UDA) improves classification performance on an unlabeled target domain through explicit discrepancy minimization of data distribution or adversarial…

计算机视觉与模式识别 · 计算机科学 2021-12-06 Shengjia Zhang , Tiancheng Lin , Yi Xu

Active domain adaptation (ADA) aims to improve the model adaptation performance by incorporating active learning (AL) techniques to label a maximally-informative subset of target samples. Conventional AL methods do not consider the…

计算机视觉与模式识别 · 计算机科学 2023-07-24 Duojun Huang , Jichang Li , Weikai Chen , Junshi Huang , Zhenhua Chai , Guanbin Li

Standard Unsupervised Domain Adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target but usually requires simultaneous access to both source and target data. Moreover, UDA approaches commonly assume…

计算机视觉与模式识别 · 计算机科学 2024-04-17 Mattia Litrico , Davide Talon , Sebastiano Battiato , Alessio Del Bue , Mario Valerio Giuffrida , Pietro Morerio

Unsupervised domain adaptation (UDA) is a statistical learning problem when the distribution of training (source) data is different from that of test (target) data. In this setting, one has access to labeled data only from the source domain…

机器学习 · 计算机科学 2026-02-24 Seonghwi Kim , Sung Ho Jo , Wooseok Ha , Minwoo Chae

Unsupervised domain adaptation (UDA) for semantic segmentation addresses the cross-domain problem with fine source domain labels. However, the acquisition of semantic labels has always been a difficult step, many scenarios only have weak…

计算机视觉与模式识别 · 计算机科学 2022-10-06 Shengjie Liu , Chuang Zhu , Wenqi Tang

Domain Adaptation methodologies have shown to effectively generalize from a labeled source domain to a label scarce target domain. Previous research has either focused on unlabeled domain adaptation without any target supervision or…

机器学习 · 计算机科学 2022-02-14 Jonas Sonntag , Gunnar Behrens , Lars Schmidt-Thieme

One of the central problems in machine learning is domain adaptation. Unlike past theoretical work, we consider a new model for subpopulation shift in the input or representation space. In this work, we propose a provably effective…

机器学习 · 计算机科学 2021-07-21 Tianle Cai , Ruiqi Gao , Jason D. Lee , Qi Lei

Deep learning models usually require a large amount of labeled data to achieve satisfactory performance. In multimedia analysis, domain adaptation studies the problem of cross-domain knowledge transfer from a label rich source domain to a…

计算机视觉与模式识别 · 计算机科学 2021-09-10 Lei Zhu , Zhaojing Luo , Wei Wang , Meihui Zhang , Gang Chen , Kaiping Zheng

Current adversarial adaptation methods attempt to align the cross-domain features, whereas two challenges remain unsolved: 1) the conditional distribution mismatch and 2) the bias of the decision boundary towards the source domain. To solve…

计算机视觉与模式识别 · 计算机科学 2021-02-16 Can Qin , Lichen Wang , Qianqian Ma , Yu Yin , Huan Wang , Yun Fu

Multi-source unsupervised domain adaptation~(MSDA) aims at adapting models trained on multiple labeled source domains to an unlabeled target domain. In this paper, we propose a novel multi-source domain adaptation framework based on…

计算机视觉与模式识别 · 计算机科学 2021-06-21 Jianzhong He , Xu Jia , Shuaijun Chen , Jianzhuang Liu

Multi-source unsupervised domain adaptation (MS-UDA) for sentiment analysis (SA) aims to leverage useful information in multiple source domains to help do SA in an unlabeled target domain that has no supervised information. Existing…

计算与语言 · 计算机科学 2020-06-11 Yong Dai , Jian Liu , Xiancong Ren , Zenglin Xu

Unsupervised domain adaptation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Previous methods focus on learning domain-invariant features to decrease the discrepancy between the feature distributions…

机器学习 · 计算机科学 2021-06-30 Yuntao Du , Yinghao Chen , Fengli Cui , Xiaowen Zhang , Chongjun Wang

Domain adaptation methods reduce domain shift typically by learning domain-invariant features. Most existing methods are built on distribution matching, e.g., adversarial domain adaptation, which tends to corrupt feature discriminability.…

机器学习 · 计算机科学 2023-02-14 Zenan Huang , Jun Wen , Siheng Chen , Linchao Zhu , Nenggan Zheng

Domain adaptive semantic segmentation is recognized as a promising technique to alleviate the domain shift between the labeled source domain and the unlabeled target domain in many real-world applications, such as automatic pilot. However,…

计算机视觉与模式识别 · 计算机科学 2021-10-14 Fuming You , Jingjing Li , Lei Zhu , Ke Lu , Zhi Chen , Zi Huang

In recent years, there has been tremendous progress in the field of semantic segmentation. However, one remaining challenging problem is that segmentation models do not generalize to unseen domains. To overcome this problem, one either has…

计算机视觉与模式识别 · 计算机科学 2022-08-16 Robert A. Marsden , Felix Wiewel , Mario Döbler , Yang Yang , Bin Yang