Neural Network Compression

60 papers with code • 2 benchmarks • 2 datasets

This task has no description! Would you like to contribute one?

Libraries

Use these libraries to find Neural Network Compression models and implementations

Most implemented papers

Soft Weight-Sharing for Neural Network Compression

KarenUllrich/Tutorial-SoftWeightSharingForNNCompression 13 Feb 2017

The success of deep learning in numerous application domains created the de- sire to run and train them on mobile devices.

Improving Neural Network Quantization without Retraining using Outlier Channel Splitting

NervanaSystems/distiller 28 Jan 2019

The majority of existing literature focuses on training quantized DNNs, while this work examines the less-studied topic of quantizing a floating-point model without (re)training.

MUSCO: Multi-Stage Compression of neural networks

juliagusak/musco 24 Mar 2019

The low-rank tensor approximation is very promising for the compression of deep neural networks.

Data-Free Learning of Student Networks

huawei-noah/Data-Efficient-Model-Compression ICCV 2019

Learning portable neural networks is very essential for computer vision for the purpose that pre-trained heavy deep models can be well applied on edge devices such as mobile phones and micro sensors.

Learning Filter Basis for Convolutional Neural Network Compression

ofsoundof/learning_filter_basis ICCV 2019

Convolutional neural networks (CNNs) based solutions have achieved state-of-the-art performances for many computer vision tasks, including classification and super-resolution of images.

ZeroQ: A Novel Zero Shot Quantization Framework

amirgholami/ZeroQ CVPR 2020

Importantly, ZeroQ has a very low computational overhead, and it can finish the entire quantization process in less than 30s (0. 5\% of one epoch training time of ResNet50 on ImageNet).

Diversity Networks: Neural Network Compression Using Determinantal Point Processes

nobug-code/Diversity_Networks_CNN_Pytorch 16 Nov 2015

We introduce Divnet, a flexible technique for learning networks with diverse neurons.

Weightless: Lossy Weight Encoding For Deep Neural Network Compression

cambridge-mlg/miracle 13 Nov 2017

This results in up to a 1. 51x improvement over the state-of-the-art.

Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameters

cambridge-mlg/miracle ICLR 2019

While deep neural networks are a highly successful model class, their large memory footprint puts considerable strain on energy consumption, communication bandwidth, and storage requirements.

A Closer Look at Structured Pruning for Neural Network Compression

BayesWatch/pytorch-prunes 10 Oct 2018

Structured pruning is a popular method for compressing a neural network: given a large trained network, one alternates between removing channel connections and fine-tuning; reducing the overall width of the network.