Results 41 to 50 of about 3,593,017 (294)

Unsupervised Domain Adaptation by Backpropagation

open access: yesCoRR, 2014
Top-performing deep architectures are trained on massive amounts of labeled data. In the absence of labeled data for a certain task, domain adaptation often provides an attractive option given that labeled data of similar nature but from a different domain (e.g. synthetic images) are available.
Yaroslav Ganin, Victor S. Lempitsky
openaire   +4 more sources

Cross-Domain Error Minimization for Unsupervised Domain Adaptation [PDF]

open access: yes, 2021
Accepted by DASFAA ...
Yuntao Du 0001   +4 more
openaire   +4 more sources

Generative Adversarial Models for Unsupervised Domain Adaptation in Semantic Segmentation [PDF]

open access: yes, 2022
In this thesis we implement an unsupervised domain adaptation framework designed for semantic segmentation and tested in a synthetic-to-real adaptation scenario. First, we propose a pixel-level adaptation strategy based on a cross-domain image mapping to
Toldo, Marco
core  

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

Deep Adversarial-Reconstruction-Classification Networks for Unsupervised Domain Adaptation [PDF]

open access: yesJisuanji kexue yu tansuo, 2022
Recently, a new method of transfer learning called adversarial domain adaptation, embeds the idea of the generative adversarial networks (GAN) into the deep networks.
LIN Jiawei, WANG Shitong
doaj   +1 more source

Unsupervised Intralingual and Cross-Lingual Speaker Adaptation for HMM-Based Speech Synthesis Using Two-Pass Decision Tree Construction [PDF]

open access: yes, 2010
Hidden Markov model (HMM)-based speech synthesis systems possess several advantages over concatenative synthesis systems. One such advantage is the relative ease with which HMM-based systems are adapted to speakers not present in the training dataset ...
Matthew Gibson, William Byrne
core   +2 more sources

Unsupervised Transductive Domain Adaptation

open access: yesCoRR, 2016
Supervised learning with large scale labeled datasets and deep layered models has made a paradigm shift in diverse areas in learning and recognition. However, this approach still suffers generalization issues under the presence of a domain shift between the training and the test data distribution.
Ozan Sener   +3 more
openaire   +2 more sources

Unsupervised Domain Adaptation for SAR Target Detection

open access: yesIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021
Recent years have witnessed great progress in synthetic aperture radar (SAR) target detection methods based on deep learning. However, these methods generally assume the training data and test data obey the same distribution, which does not always hold ...
Yu Shi, Lan Du, Yuchen Guo
doaj   +1 more source

Contrastive Adaptation Network for Unsupervised Domain Adaptation [PDF]

open access: yes2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019
Accepted by CVPR ...
Guoliang Kang   +3 more
openaire   +4 more sources

A Survey of Unsupervised Deep Domain Adaptation [PDF]

open access: yesACM Transactions on Intelligent Systems and Technology, 2020
Deep learning has produced state-of-the-art results for a variety of tasks. While such approaches for supervised learning have performed well, they assume that training and testing data are drawn from the same distribution, which may not always be the case.
Garrett Wilson, Diane J. Cook
openaire   +3 more sources

Home - About - Disclaimer - Privacy