Results 31 to 40 of about 8,068,927 (352)

Maximum Classifier Discrepancy for Unsupervised Domain Adaptation [PDF]

open access: yes2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2017
In this work, we present a method for unsupervised domain adaptation. Many adversarial learning methods train domain classifier networks to distinguish the features as either a source or target and train a feature generator network to mimic the ...
Kuniaki Saito   +3 more
semanticscholar   +1 more source

A Comprehensive Survey on Source-Free Domain Adaptation [PDF]

open access: yesIEEE 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
Jing-Jing Li   +4 more
semanticscholar   +1 more source

Adaptive Contrastive Learning with Label Consistency for Source Data Free Unsupervised Domain Adaptation

open access: yesSensors, 2022
Unsupervised domain adaptation, which aims to alleviate the domain shift between source domain and target domain, has attracted extensive research interest; however, this is unlikely in practical application scenarios, which may be due to privacy issues ...
Xuejun Zhao   +6 more
doaj   +1 more source

CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation [PDF]

open access: yesInternational Conference on Learning Representations, 2021
Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a labeled source domain to a different unlabeled target domain. Most existing UDA methods focus on learning domain-invariant feature representation, either from the domain level
Tongkun Xu   +5 more
semanticscholar   +1 more source

Spectral Normalization for Domain Adaptation

open access: yesInformation, 2020
The transfer learning method is used to extend our existing model to more difficult scenarios, thereby accelerating the training process and improving learning performance.
Liquan Zhao, Yan Liu
doaj   +1 more source

Benchmarking Domain Adaptation Methods on Aerial Datasets

open access: yesSensors, 2021
Deep learning grew in importance in recent years due to its versatility and excellent performance on supervised classification tasks. A core assumption for such supervised approaches is that the training and testing data are drawn from the same ...
Navya Nagananda   +6 more
doaj   +1 more source

ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation [PDF]

open access: yesComputer Vision and Pattern Recognition, 2018
Semantic segmentation is a key problem for many computer vision tasks. While approaches based on convolutional neural networks constantly break new records on different benchmarks, generalizing well to diverse testing environments remains a major ...
Tuan-Hung Vu   +4 more
semanticscholar   +1 more source

Unsupervised Domain Adaptation for 3D Point Clouds by Searched Transformations

open access: yesIEEE Access, 2022
Input-level domain adaptation reduces the burden of a neural encoder without supervision by reducing the domain gap at the input level. Input-level domain adaptation is widely employed in 2D visual domain, e.g., images and videos, but is not utilized for
Dongmin Kang   +3 more
doaj   +1 more source

SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation [PDF]

open access: yesComputer Vision and Pattern Recognition, 2022
Adapting to a continuously evolving environment is a safety-critical challenge inevitably faced by all autonomous-driving systems. Existing image- and video-based driving datasets, however, fall short of capturing the mutable nature of the real world. In
Tao Sun   +7 more
semanticscholar   +1 more source

Review of Studies on Domain Adaptation [PDF]

open access: yesJisuanji gongcheng, 2021
Classical machine learning algorithms assume that the training and testing instances share the same input feature space and data distribution.In many real-world applications, however, this assumption cannot be satisfied, resulting in the failure of the ...
LI Jingjing, MENG Lichao, ZHANG Ke, LU Ke, SHEN Hengtao
doaj   +1 more source

Home - About - Disclaimer - Privacy