A
Andrew Rabinovich
Researcher at Google
Publications - 67
Citations - 51886
Andrew Rabinovich is an academic researcher from Google. The author has contributed to research in topics: Convolutional neural network & Artificial neural network. The author has an hindex of 28, co-authored 67 publications receiving 37872 citations. Previous affiliations of Andrew Rabinovich include University of California, San Diego & Discovery Institute.
Papers
More filters
Posted Content
Training Deep Neural Networks on Noisy Labels with Bootstrapping
TL;DR: The authors proposed a generic way to handle noisy and incomplete labeling by augmenting the prediction objective with a notion of consistency, where a prediction consistent if the same prediction is made given similar percepts, where the notion of similarity is between deep network features computed from the input data.
Proceedings Article
Training deep neural networks on noisy labels with bootstrapping
TL;DR: This article proposed a generic way to handle noisy and incomplete labeling by augmenting the prediction objective with a notion of consistency, where the notion of similarity is between deep network features computed from the input data.
Posted Content
Deep Image Homography Estimation
TL;DR: Two convolutional neural network architectures are presented for HomographyNet: a regression network which directly estimates the real-valued homography parameters, and a classification network which produces a distribution over quantized homographies.
Patent
Facial recognition with social network aiding
TL;DR: In this paper, a facial recognition search system identifies one or more likely names (or other personal identifiers) corresponding to the facial image(s) in a query as follows: after receiving the visual query with one or multiple facial images, the system identifies images that potentially match the respective facial image in accordance with visual similarity criteria.
Proceedings ArticleDOI
RoomNet: End-to-End Room Layout Estimation
TL;DR: This paper predicts the locations of the room layout keypoints using RoomNet, an end-to-end trainable encoder-decoder network and presents optional extensions to the RoomNet architecture such as including recurrent computations and memory units to refine the keypoint locations under the same parametric capacity.