Saurabh Singh

Saurabh Singh

I am a researcher working in the field of Computer Vision and Machine Learning. My current work focuses on lossy multimedia compression using Deep Neural Networks. I was a PhD candidate advised by David Forsyth and Derek Hoiem in the Computer Science Department at University of Illinois, Urbana-Champaign. I interned at Google Research in 2013. I received my MS from Robotics Institute, Carnegie Mellon University in 2011 where I worked with Alyosha Efros, Abhinav Gupta and Martial Hebert. My earlier research focused on discovery and use of context for various tasks including classification, pose estimation, localizing landmarks with little local appearance and visual question answering.
Authored Publications
Sort By
  • Title
  • Title, descending
  • Year
  • Year, descending
    Google
Nonlinear Transform Coding
Johannes Ballé
Philip A. Chou
Sung Jin Hwang
IEEE Trans. on Special Topics in Signal Processing, 15 (2021) (to appear)
End-to-end Learning of Compressible Features
Johannes Ballé
Abhinav Shrivastava
2020 IEEE Int. Conf. on Image Processing (ICIP)
Deep Implicit Volume Compression
Danhang "Danny" Tang
Phil Chou
Christian Haene
Mingsong Dou
Jonathan Taylor
Shahram Izadi
Sofien Bouaziz
Cem Keskin
CVPR (2020)
Scalable Model Compression by Entropy Penalized Reparameterization
Deniz Oktay
Johannes Ballé
Abhinav Shrivastava
8th Int. Conf. on Learning Representations (ICLR) (2020)
Variational Image Compression with a Scale Hyperprior
Johannes Ballé
Sung Jin Hwang
6th Int. Conf. on Learning Representations (ICLR) (2018)
Spatially adaptive image compression using a tiled deep network
Michele Covell
Joel Shor
Sung Jin Hwang
Damien Vincent
Proceedings of the International Conference on Image Processing (2017), pp. 2796-2800
No Fuss Distance Metric Learning using Proxies
Alexander Toshev
Sergey Ioffe
International Conference on Computer Vision (ICCV), IEEE (2017)