Saurabh Singh Picture

Saurabh Singh

http://www.saurabhsingh.info

Saurabh Singh

I am a Senior Research Scientist at Google, working in the field of Computer Vision and Machine Learning. I received my PhD in Computer Science from University of Illinois at Urbana-Champaign, where I was advised by Prof. David Forsyth and Prof. Derek Hoiem. I received my MS from Robotics Institute, Carnegie Mellon University where I worked with Alyosha Efros, Abhinav Gupta and Martial Hebert.

I frequently serve as an area chair or reviewer at leading computer vision and ML conferences, including CVPR, ICCV, ECCV, ICLR and NeurIPS.

Personal website of Saurabh Singh.

Selected Papers

Publications

new Stochastic Sampling from Deterministic Flow Models
Saurabh Singh, Ian Fischer

[arXiv]
new Fourier Head: Helping Large Language Models Learn Complex Probability Distributions
Nate Gillman, Daksh Aggarwal, Michael Freeman, Saurabh Singh, Chen Sun, ICLR 2025

[arXiv]
new Fourier Basis Density Model Best Paper Award
Alfredo De la Fuente, Saurabh Singh, Johannes Ballé, PCS 2024

[arXiv]
Weighted Ensemble Self-Supervised Learning
Yangjun Ruan, Saurabh Singh, Warren Morningstar, Alexander A. Alemi, Sergey Ioffe, Ian Fischer, Joshua V. Dillon, ICLR 2023

[arXiv]
LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification
Sharath Girish, Kamal Gupta, Saurabh Singh, Abhinav Shrivastava, ICLR 2023

[arXiv]
Trajectory ensembling for fine tuning - performance gains without modifying training
Louise Anderson-Conway, Vighnesh Birodkar, Saurabh Singh, Hossein Mobahi, Alexander A Alemi, HITY Workshop NeurIPS 2022

[openreview]
3D Scene Compression through Entropy Penalized Neural Representation Functions
Thomas Bird, Johannes Ballé, Saurabh Singh, Philip A. Chou, Picture Coding Symposium (PCS) 2021

[arXiv]
Nonlinear Transform Coding
Johannes Ballé, Philip A. Chou, David Minnen, Saurabh Singh, Nick Johnston, Eirikur Agustsson, Sung Jin Hwang, George Toderici

[arXiv]
End-to-end Learning of Compressible Features
Saurabh Singh, Sami Abu-El-Haija, Nick Johnston, Johannes Ballé, Abhinav Shrivastava, George Toderici, ICIP 2020

[arXiv]
Channel-wise Autoregressive Entropy Models for Learned Image Compression
David Minnen, Saurabh Singh, ICIP 2020

[arXiv]
Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural Networks
Saurabh Singh, Shankar Krishnan, CVPR 2020

[arXiv]
Deep Implicit Volume Compression
Danhang Tang*, Saurabh Singh*, Philip Chou, Christian Haene, Andrea Tagliasacchi, Mingsong Dou, Sean Fanello, Jonathan Taylor, Philip Davidson, Onur Guleryuz, Yinda Zhang, Shahram Izadi, Sofien Bouaziz, Cem Keskin, CVPR 2020

[arXiv] [project page] [video]
PatchVAE: Learning Local Latent Codes for Recognition
Kamal Gupta, Saurabh Singh, Abhinav Shrivastava, CVPR 2020

[arXiv]
Scalable Model Compression by Entropy Penalized Reparameterization
Deniz Oktay, Johannes Ballé, Saurabh Singh, Abhinav Shrivastava, ICLR 2020

[arXiv]
EvalNorm: Estimating Batch Normalization Statistics for Evaluation
Saurabh Singh, Abhinav Shrivastava, ICCV 2019

[arXiv]
Image-Dependent Local Entropy Models for Learned Image Compression
David Minnen, George Toderici, Saurabh Singh, Sung Jin Hwang, Michele Covell, ICIP 2018

[arXiv]
Variational image compression with a scale hyperprior
Johannes Ballé, David Minnen, Saurabh Singh, Sung Jin Hwang, Nick Johnston, ICLR 2018

[arXiv]
Improved lossy image compression with priming and spatially adaptive bit rates for recurrent networks
Nick Johnston, Damien Vincent, David Minnen, Michele Covell, Saurabh Singh, Troy Chinen, CVPR 2018

[arXiv]
Spatially adaptive image compression using a tiled deep network
David Minnen, George Toderici, Michele Covell, Troy Chinen, Nick Johnston, Joel Shor, Sung Jin Hwang, Damien Vincent, Saurabh Singh, ICIP 2017

[arXiv]
Target-quality image compression with recurrent, convolutional neural networks
Michele Covell, Nick Johnston, David Minnen, Sung Jin Hwang, Joel Shor, Saurabh Singh, Damien Vincent

[arXiv]
Revisiting unreasonable effectiveness of data in deep learning era
Chen Sun, Abhinav Shrivastava, Saurabh Singh, Abhinav Gupta, ICCV 2017

[arXiv]
Aligned image-word representations improve inductive transfer across vision-language tasks
Tanmay Gupta, Kevin J. Shih, Saurabh Singh, Derek Hoiem, ICCV 2017

[arXiv]
No fuss distance metric learning using proxies
Yair Movshovitz-Attias, Alexander Toshev, Thomas Leung, Sergey Ioffe, Saurabh Singh, ICCV 2017

[arXiv]
Learning to localize landmarks
Saurabh Singh, PhD Thesis ,University of Illinois at Urbana-Champaign 2016

[link]
Swapout: Learning an ensemble of deep architectures
Saurabh Singh, Derek Hoiem, David Forsyth, NeurIPS 2016

[arXiv]
Learning to localize little landmarks
Saurabh Singh, Derek Hoiem, David Forsyth, CVPR 2016

[project page]
Where to look: Focus regions for visual question answering
Kevin J. Shih, Saurabh Singh, Derek Hoiem, CVPR 2016

[arXiv]
What makes Paris look like Paris?
Carl Doersch, Saurabh Singh, Abhinav Gupta, Josef Sivic, Alexei A. Efros, Communications of the ACM 2015

[short paper]
Part localization using multi-proposal consensus for fine-grained categorization
Kevin J. Shih, Arun Mallya, Saurabh Singh, Derek Hoiem, BMVC 2015

[arXiv]
Learning a sequential search for landmarks
Saurabh Singh, Derek Hoiem, David Forsyth, CVPR 2015

[project page]
What makes paris look like paris?
Carl Doersch, Saurabh Singh, Abhinav Gupta, Josef Sivic, Alexei A. Efros, ACM TOG SIGGRAPH 2012

[project page]
Unsupervised Discovery of Mid-Level Discriminative Patches
Saurabh Singh, Abhinav Gupta, Alexei A. Efros, ECCV 2012

[arXiv] [project page]
Constrained Semi-Supervised Learning Using Attributes and Comparative Attributes
Abhinav Shrivastava, Saurabh Singh, Abhinav Gupta, ECCV 2012

[project page]