Results 11 to 20 of about 4,969,023 (298)
Adversarial Discriminative Domain Adaptation [PDF]
Computer Vision and Pattern Recognition, 2017 Adversarial learning methods are a promising approach to training robust deep networks, and can generate complex samples across diverse domains. They also can improve recognition despite the presence of domain shift or dataset bias: several adversarial ...
Darrell, Trevor +3 more
core +2 more sources
Return of Frustratingly Easy Domain Adaptation [PDF]
AAAI Conference on Artificial Intelligence, 2015 Unlike human learning, machine learning often fails to handle changes between training (source) and test (target) input distributions. Such domain shifts, common in practical scenarios, severely damage the performance of conventional machine learning ...
Feng, Jiashi, Saenko, Kate, Sun, Baochen
core +2 more sources
Continual Test-Time Domain Adaptation [PDF]
Computer Vision and Pattern Recognition, 2022 Test-time domain adaptation aims to adapt a source pre-trained model to a target domain without using any source data. Existing works mainly consider the case where the target domain is static.
Qin Wang +3 more
semanticscholar +1 more source
MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation [PDF]
Computer Vision and Pattern Recognition, 2022 In unsupervised domain adaptation (UDA), a model trained on source data (e.g. synthetic) is adapted to target data (e.g. real-world) without access to target annotation.
Lukas Hoyer +3 more
semanticscholar +1 more source
Source-Free Domain Adaptation for Semantic Segmentation [PDF]
Computer Vision and Pattern Recognition, 2021 Unsupervised Domain Adaptation (UDA) can tackle the challenge that convolutional neural network (CNN)-based approaches for semantic segmentation heavily rely on the pixel-level annotated data, which is labor-intensive. However, existing UDA approaches in
Yuang Liu, Wei Zhang, Jun Wang
semanticscholar +1 more source
A Comprehensive Survey on Source-Free Domain Adaptation [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023 Over the past decade, domain adaptation has become a widely studied branch of transfer learning which aims to improve performance on target domains by leveraging knowledge from the source domain. Conventional domain adaptation methods often assume access
Zhiqi Yu +4 more
semanticscholar +1 more source
Generalized Source-free Domain Adaptation [PDF]
IEEE International Conference on Computer Vision, 2021 Domain adaptation (DA) aims to transfer the knowledge learned from a source domain to an unlabeled target domain. Some recent works tackle source-free domain adaptation (SFDA) where only a source pre-trained model is available for adaptation to the ...
Shiqi Yang +4 more
semanticscholar +1 more source
Domain Adaptation for Medical Image Analysis: A Survey [PDF]
IEEE Transactions on Biomedical Engineering, 2021 Machine learning techniques used in computer-aided medical image analysis usually suffer from the domain shift problem caused by different distributions between source/reference data and target data.
Hao Guan, Mingxia Liu
semanticscholar +1 more source
Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation [PDF]
Neural Information Processing Systems, 2022 We propose a simple but effective source-free domain adaptation (SFDA) method. Treating SFDA as an unsupervised clustering problem and following the intuition that local neighbors in feature space should have more similar predictions than other features,
Shiqi Yang +4 more
semanticscholar +1 more source
Moment Matching for Multi-Source Domain Adaptation [PDF]
IEEE International Conference on Computer Vision, 2018 Conventional unsupervised domain adaptation (UDA) assumes that training data are sampled from a single domain. This neglects the more practical scenario where training data are collected from multiple sources, requiring multi-source domain adaptation. We
Xingchao Peng +5 more
semanticscholar +1 more source