1.4k citations · 1.7k across the 9 of their papers we have counts for
16 papers
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…
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…
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…
Channel-wise Autoregressive Entropy Models for Learned Image Compression
David Minnen, Saurabh Singh
In learning-based approaches to image compression, codecs are developed by optimizing a computational model to minimize a rate-distortion objective. Currently, the most effective l…
Nonlinear Transform Coding
Johannes Ballé, Philip A. Chou, David Minnen +5
We review a class of methods that can be collected under the name nonlinear transform coding (NTC), which over the past few years have become competitive with the best linear trans…
Deep Implicit Volume Compression
Danhang Tang, Saurabh Singh, Philip A. Chou +11
We describe a novel approach for compressing truncated signed distance fields (TSDF) stored in 3D voxel grids, and their corresponding textures. To compress the TSDF, our method re…
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…
Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural Networks
Saurabh Singh, Shankar Krishnan
Batch Normalization (BN) uses mini-batch statistics to normalize the activations during training, introducing dependence between mini-batch elements. This dependency can hurt the p…
Scalable Model Compression by Entropy Penalized Reparameterization
Deniz Oktay, Johannes Ballé, Saurabh Singh +1
We describe a simple and general neural network weight compression approach, in which the network parameters (weights and biases) are represented in a "latent" space, amounting to…
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…
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…
Spatially adaptive image compression using a tiled deep network
David Minnen, George Toderici, Michele Covell +6
Deep neural networks represent a powerful class of function approximators that can learn to compress and reconstruct images. Existing image compression algorithms based on neural n…
Variational image compression with a scale hyperprior
Johannes Ballé, David Minnen, Saurabh Singh +2
We describe an end-to-end trainable model for image compression based on variational autoencoders. The model incorporates a hyperprior to effectively capture spatial dependencies i…
Revisiting Unreasonable Effectiveness of Data in Deep Learning Era
Chen Sun, Abhinav Shrivastava, Saurabh Singh +1
The success of deep learning in vision can be attributed to: (a) models with high capacity; (b) increased computational power; and (c) availability of large-scale labeled data. Sin…
Target-Quality Image Compression with Recurrent, Convolutional Neural Networks
Michele Covell, Nick Johnston, David Minnen +5
We introduce a stop-code tolerant (SCT) approach to training recurrent convolutional neural networks for lossy image compression. Our methods introduce a multi-pass training method…
Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks
Nick Johnston, Damien Vincent, David Minnen +6
We propose a method for lossy image compression based on recurrent, convolutional neural networks that outperforms BPG (4:2:0 ), WebP, JPEG2000, and JPEG as measured by MS-SSIM. We…