Results 41 to 50 of about 1,144,226 (279)

Bilateral co-transfer for unsupervised domain adaptation

Journal of Automation and Intelligence, 2023
Labeled data scarcity of an interested domain is often a serious problem in machine learning. Leveraging the labeled data from other semantic-related yet co-variate shifted source domain to facilitate the interested domain is a consensus.
Fuxiang Huang, Jingru Fu, Lei Zhang
doaj   +1 more source

Theoretic Analysis and Extremely Easy Algorithms for Domain Adaptive Feature Learning

, 2017
Domain adaptation problems arise in a variety of applications, where a training dataset from the \textit{source} domain and a test dataset from the \textit{target} domain typically follow different distributions.
Chung, Fu-lai, Deng, Cheng, Huang, Heng, Jiang, Wenhao, Liu, Wei, Nie, Feiping   +5 more
core   +1 more source

Domain Adaptation for Statistical Classifiers

, 2011
The most basic assumption used in statistical learning theory is that training data and test data are drawn from the same underlying distribution. Unfortunately, in many applications, the "in-domain" test data is drawn from a distribution that is related,
Daume III, H., Marcu, D.
core   +1 more source

Wasserstein Distance Guided Representation Learning for Domain Adaptation

, 2018
Domain adaptation aims at generalizing a high-performance learner on a target domain via utilizing the knowledge distilled from a source domain which has a different but related data distribution.
Qu, Yanru, Shen, Jian, Yu, Yong, Zhang, Weinan   +3 more
core   +1 more source

Meta Domain Adaptation Approach for Multi-Domain Ranking

IEEE Access
In a real industry recommendation system, the distribution of recommended domains is very redundant. Different domains may address the same problem, such as the Click-Through Rate (CTR) prediction, and may share the same features.
Zihan Xia, Yixuan Liu, Xiangran Zhang, Xiaoshuang Sheng, Kewei Liang   +4 more
doaj   +1 more source

Self-Supervised Domain Adaptation for Computer Vision Tasks

IEEE Access, 2019
Recent progress of self-supervised visual representation learning has achieved remarkable success on many challenging computer vision benchmarks. However, whether these techniques can be used for domain adaptation has not been explored.
Jiaolong Xu, Liang Xiao, Antonio M. Lopez   +2 more
doaj   +1 more source

Frequency-Domain Fusing Convolutional Neural Network: A Unified Architecture Improving Effect of Domain Adaptation for Fault Diagnosis

Sensors, 2021
In recent years, transfer learning has been widely applied in fault diagnosis for solving the problem of inconsistent distribution of the original training dataset and the online-collecting testing dataset. In particular, the domain adaptation method can
Xudong Li, Jianhua Zheng, Mingtao Li, Wenzhen Ma, Yang Hu   +4 more
doaj   +1 more source

Zero-Shot Deep Domain Adaptation

, 2018
Domain adaptation is an important tool to transfer knowledge about a task (e.g. classification) learned in a source domain to a second, or target domain. Current approaches assume that task-relevant target-domain data is available during training.
B Sun, K Saenko, M Ghifary, P Arbelaez, R Aljundi, Y Ganin, Y LeCun, Z Ding   +7 more
core   +1 more source

Distribution matching and structure preservation for domain adaptation

Complex & Intelligent Systems, 2022
Cross-domain classification refers to completing the corresponding classification task in a target domain which lacks label information, by exploring useful knowledge in a related source domain but with different data distribution.
Ping Li, Zhiwei Ni, Xuhui Zhu, Juan Song
doaj   +1 more source

Dynamic Adaptation on Non-Stationary Visual Domains

, 2018
Domain adaptation aims to learn models on a supervised source domain that perform well on an unsupervised target. Prior work has examined domain adaptation in the context of stationary domain shifts, i.e. static data sets.
B Moiseev, B Sun, C Tan, LC Chen, M Ghifary, M Tennant, SR Richter, T Tommasi, Y Ganin, Y LeCun, Y Wang   +10 more
core   +1 more source