A
Anoop Korattikara
Researcher at Google
Publications - 20
Citations - 4022
Anoop Korattikara is an academic researcher from Google. The author has contributed to research in topics: Bayesian probability & Artificial neural network. The author has an hindex of 14, co-authored 20 publications receiving 3399 citations. Previous affiliations of Anoop Korattikara include University of California, Irvine.
Papers
More filters
Proceedings ArticleDOI
Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors
Jonathan Huang,Vivek Rathod,Chen Sun,Menglong Zhu,Anoop Korattikara,Alireza Fathi,Ian Fischer,Zbigniew Wojna,Yang Song,Sergio Guadarrama,Kevin Murphy +10 more
TL;DR: A unified implementation of the Faster R-CNN, R-FCN and SSD systems is presented and the speed/accuracy trade-off curve created by using alternative feature extractors and varying other critical parameters such as image size within each of these meta-architectures is traced out.
Proceedings ArticleDOI
Im2Calories: Towards an Automated Mobile Vision Food Diary
Austin Myers,Nick Johnston,Vivek Rathod,Anoop Korattikara,Alexander Gorban,Nathan Silberman,Sergio Guadarrama,George Papandreou,Jonathan Huang,Kevin Murphy +9 more
TL;DR: A system which can recognize the contents of your meal from a single image, and then predict its nutritional contents, such as calories, is presented, significantly outperforming previous work.
Proceedings Article
Austerity in MCMC Land: Cutting the Metropolis-Hastings Budget
TL;DR: In this paper, an approximate MH rule based on a sequential hypothesis test was proposed to accept or reject samples with high confidence using only a fraction of the data required for the exact MH rule.
Posted Content
Speed/accuracy trade-offs for modern convolutional object detectors
Jonathan Huang,Vivek Rathod,Chen Sun,Menglong Zhu,Anoop Korattikara,Alireza Fathi,Ian Fischer,Zbigniew Wojna,Yang Song,Sergio Guadarrama,Kevin Murphy +10 more
TL;DR: In this article, the authors investigate various ways to trade accuracy for speed and memory usage in modern convolutional object detection systems, and present a unified implementation of the Faster R-CNN, R-FCN and SSD systems, which they view as "meta-architectures".
Proceedings Article
Bayesian dark knowledge
TL;DR: This work describes a method for "distilling" a Monte Carlo approximation to the posterior predictive density into a more compact form, namely a single deep neural network.