activity
20172022
most citedRevisiting Unreasonable Effectiveness of Data in Deep Learning Era

304 citations · 351 across the 6 of their papers we have counts for

collaborators
Showing cs.CVShow all

10 papers · 1 filter

cs.CV20227 cited

LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification

Sharath Girish, Kamal Gupta, Saurabh Singh +1

We introduce LilNetX, an end-to-end trainable technique for neural networks that enables learning models with specified accuracy-rate-computation trade-off. Prior works approach th…

cs.CV2021

3D Scene Compression through Entropy Penalized Neural Representation Functions

Thomas Bird, Johannes Ballé, Saurabh Singh +1

Some forms of novel visual media enable the viewer to explore a 3D scene from arbitrary viewpoints, by interpolating between a discrete set of original views. Compared to 2D imager…

cs.CV2020

End-to-end Learning of Compressible Features

Saurabh Singh, Sami Abu-El-Haija, Nick Johnston +3

Pre-trained convolutional neural networks (CNNs) are powerful off-the-shelf feature generators and have been shown to perform very well on a variety of tasks. Unfortunately, the ge…

cs.CV2020

PatchVAE: Learning Local Latent Codes for Recognition

Kamal Gupta, Saurabh Singh, Abhinav Shrivastava

Unsupervised representation learning holds the promise of exploiting large amounts of unlabeled data to learn general representations. A promising technique for unsupervised learni…

cs.CV2019

EvalNorm: Estimating Batch Normalization Statistics for Evaluation

Saurabh Singh, Abhinav Shrivastava

Batch normalization (BN) has been very effective for deep learning and is widely used. However, when training with small minibatches, models using BN exhibit a significant degradat…

cs.CV2018

Image-Dependent Local Entropy Models for Learned Image Compression

David Minnen, George Toderici, Saurabh Singh +2

The leading approach for image compression with artificial neural networks (ANNs) is to learn a nonlinear transform and a fixed entropy model that are optimized for rate-distortion…