Y
Yoshitaka Ushiku
Researcher at Omron
Publications - 91
Citations - 6198
Yoshitaka Ushiku is an academic researcher from Omron. The author has contributed to research in topics: Computer science & Feature vector. The author has an hindex of 23, co-authored 77 publications receiving 3958 citations. Previous affiliations of Yoshitaka Ushiku include University of Tokyo.
Papers
More filters
Proceedings ArticleDOI
Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
TL;DR: MCD-DA as discussed by the authors aligns distributions of source and target by utilizing the task-specific decision boundaries between classes to detect target samples that are far from the support of the source.
Proceedings ArticleDOI
Neural 3D Mesh Renderer
TL;DR: In this article, an approximate gradient for rasterization is proposed to enable the integration of rendering into neural networks, which enables single-image 3D mesh reconstruction with silhouette image supervision.
Proceedings ArticleDOI
Strong-Weak Distribution Alignment for Adaptive Object Detection
TL;DR: This work proposes an approach for unsupervised adaptation of object detectors from label-rich to label-poor domains which can significantly reduce annotation costs associated with detection, and designs the strong domain alignment model to only look at local receptive fields of the feature map.
Proceedings Article
Asymmetric tri-training for unsupervised domain adaptation
TL;DR: This work proposes the use of an asymmetric tri-training method for unsupervised domain adaptation, where two networks are used to label unlabeled target samples, and one network is trained by the pseudo-labeled samples to obtain target-discriminative representations.
Posted Content
Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
TL;DR: The authors align distributions of source and target by utilizing the task-specific decision boundaries between classes, which is a method for unsupervised domain adaptation, which outperforms other methods on several datasets of image classification and semantic segmentation.