深度模型压缩优化论文汇总

A White Paper on Neural Network Quantization

A Survey of Model Compression and Acceleration for Deep Neural Networks

A Survey of Quantization Methods for Efficient Neural Network Inference

Convolutional neural networks with low-rank regularization

Coordinating filters for faster deep neural networks.

Darkrank: Accelerating deep metric learning via cross sample similarities transfer

Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding.

Distilling the Knowledge in a Neural Network

Fitnets: Hints for thin deep nets

Faster cnns with direct sparse convolutions and guided pruning

Hardware-oriented approximation of convolutional neural networks.

Incremental network quantization: Towards lossless cnns with low-precision weights

Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks

Like what you like: Knowledge distill via neuron selectivity transfer

Learning both weights and connections for efficient neural network

Learning Efficient Convolutional Networks through Network Slimming

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

Pruning filters for efficient convnets

Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer.

Pruning Convolutional Neural Networks for Resource Efficient Inference

Quantized convolutional neural networks for mobile devices

Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

SqueezeNet ：AlexNet-level accuracy with 50x fewer parameters and <0.5MB

Thinet: A filter level pruning method for deep neural network compression.

Towards lightweight convolutional neural networks for object detection

Xnor-net: Imagenet classification using binary convolutional neura lnetworks.

Xception: Deep Learning with Depthwise Separable Convolutions