Results 51 to 60 of about 8,068,927 (352)

ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection [PDF]

open access: yesComputer Vision and Pattern Recognition, 2021
We present a new domain adaptive self-training pipeline, named ST3D, for unsupervised domain adaptation on 3D object detection from point clouds. First, we pre-train the 3D detector on the source domain with our proposed random object scaling strategy ...
Jihan Yang   +4 more
semanticscholar   +1 more source

Heuristic Domain Adaptation

open access: yesCoRR, 2020
In visual domain adaptation (DA), separating the domain-specific characteristics from the domain-invariant representations is an ill-posed problem. Existing methods apply different kinds of priors or directly minimize the domain discrepancy to address this problem, which lack flexibility in handling real-world situations.
Shuhao Cui   +4 more
openaire   +4 more sources

Unsupervised Domain Adaptation Using Exemplar-SVMs with Adaptation Regularization

open access: yesComplexity, 2018
Domain adaptation has recently attracted attention for visual recognition. It assumes that source and target domain data are drawn from the same feature space but different margin distributions and its motivation is to utilize the source domain instances
Yiwei He   +3 more
doaj   +1 more source

C2DAN: An Improved Deep Adaptation Network with Domain Confusion and Classifier Adaptation

open access: yesSensors, 2020
Deep neural networks have been successfully applied in domain adaptation which uses the labeled data of source domain to supplement useful information for target domain.
Han Sun   +5 more
doaj   +1 more source

Cross-Domain Hyperspectral Image Classification Based on Bi-Directional Domain Adaptation [PDF]

open access: yesIEEE transactions on circuits and systems for video technology (Print)
Utilizing hyperspectral remote sensing technology enables the extraction of fine-grained land cover classes. Typically, satellite or airborne images used for training and testing are acquired from different regions or times, where the same class has ...
Yu-Xiang Zhang   +5 more
semanticscholar   +1 more source

Domain Adaptation in Regression [PDF]

open access: yes, 2011
This paper presents a series of new results for domain adaptation in the regression setting. We prove that the discrepancy is a distance for the squared loss when the hypothesis set is the reproducing kernel Hilbert space induced by a universal kernel such as the Gaussian kernel.
Corinna Cortes, Mehryar Mohri
openaire   +2 more sources

OVANet: One-vs-All Network for Universal Domain Adaptation [PDF]

open access: yesIEEE International Conference on Computer Vision, 2021
Universal Domain Adaptation (UNDA) aims to handle both domain-shift and category-shift between two datasets, where the main challenge is to transfer knowledge while rejecting "unknown" classes which are absent in the labeled source data but present in ...
Kuniaki Saito, Kate Saenko
semanticscholar   +1 more source

Experiments on domain adaptation for English-Hindi SMT [PDF]

open access: yes, 2009
Statistical Machine Translation (SMT) systems are usually trained on large amounts of bilingual text and monolingual target language text. If a significant amount of out-of-domain data is added to the training data, the quality of translation can drop ...
Way, Andy   +3 more
core   +2 more sources

Test-Time Unsupervised Domain Adaptation [PDF]

open access: yes, 2020
Convolutional neural networks trained on publicly available medical imaging datasets (source domain) rarely generalise to different scanners or acquisition protocols (target domain). This motivates the active field of domain adaptation.
Orbes-Arteaga, Mauricio   +11 more
core   +3 more sources

Background-Aware Domain Adaptation for Plant Counting

open access: yesFrontiers in Plant Science, 2022
Deep learning-based object counting models have recently been considered preferable choices for plant counting. However, the performance of these data-driven methods would probably deteriorate when a discrepancy exists between the training and testing ...
Min Shi, Xing-Yi Li, Hao Lu, Zhi-Guo Cao
doaj   +1 more source

Home - About - Disclaimer - Privacy