Deep Compression/Acceleration：模型压缩加速论文汇总

2019 年 5 月 15 日 极市平台

加入极市专业CV交流群，与6000+来自腾讯，华为，百度，北大，清华，中科院等名企名校视觉开发者互动交流！更有机会与李开复老师等大牛群内互动！

同时提供每月大咖直播分享、真实项目需求对接、干货资讯汇总，行业技术交流。点击文末“阅读原文”立刻申请入群~

作者 | Mars_WH

来源 |

blog.csdn.net/hw5226349/article/details/84888416

原文 | http://bbs.cvmart.net/topics/352

深度学习（Deep Learning）因其计算复杂度或参数冗余，在一些场景和设备上限制了相应的模型部署，需要借助模型压缩、优化加速、异构计算等方法突破瓶颈。其中模型压缩算法能够有效降低参数冗余，从而减少存储占用、通信带宽和计算复杂度，有助于深度学习的应用部署，本文汇总了近几年模型压缩方面的相关研究paper，欢迎收藏阅读~

结构structure

Searching for MobileNetV3

arxiv:https://arxiv.org/abs/1905.02244v1

中文解读：重磅！MobileNetV3 来了！

[BMVC2018] IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural Networks
arxiv:https://arxiv.org/abs/1806.00178
github:https://github.com/homles11/IGCV3

[CVPR2018] IGCV2: Interleaved Structured Sparse Convolutional Neural Networks

arxiv:https://arxiv.org/abs/1804.06202

[CVPR2018] MobileNetV2: Inverted Residuals and Linear Bottlenecks

arxiv:https://arxiv.org/abs/1801.04381
github:https://github.com/tensorflow/models/tree/master/research/slim/nets/mobilenet

[ECCV2018] ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

arxiv:https://arxiv.org/abs/1807.11164

量化quantization

Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
intro:二值网络
arxiv:https://arxiv.org/abs/1602.02830
github: https://github.com/MatthieuCourbariaux/BinaryNet
https://github.com/itayhubara/BinaryNet

[ACM2017] FINN: A Framework for Fast, Scalable Binarized Neural Network Inference
intro:二值网络
pdf:http://www.idi.ntnu.no/~yamanu/2017-fpga-finn-preprint.pdf
github:https://github.com/Xilinx/FINN

[CVPR2016] DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
intro:低bit位
arxiv:https://arxiv.org/abs/1606.06160
github:https://github.com/tensorpack/tensorpack/tree/master/examples/DoReFa-Net

[CVPR2016] XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
intro:darknet团队出品
arxiv:https://arxiv.org/abs/1603.05279
github:https://github.com/allenai/XNOR-Net

[CVPR2016] Ternary Weight Networks

arxiv:https://arxiv.org/abs/1605.04711
github:https://github.com/fengfu-chris/caffe-twns

Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
Google出品
arxiv:https://arxiv.org/abs/1712.05877
github:https://github.com/tensorflow/tensorflow/tree/master/tensorflow/contrib/quantize

[ACM2017] Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
intro:QNNs
arxiv:https://arxiv.org/abs/1609.07061
github:https://github.com/peisuke/qnn

Two-Step Quantization for Low-bit Neural Networks

paper:http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Two-Step_Quantization_for_CVPR_2018_paper.pdf

剪枝pruning

通道裁剪channel pruning

[NIPS2018] Discrimination-aware Channel Pruning for Deep Neural Networks

arxiv:https://arxiv.org/abs/1810.11809
github:https://github.com/Tencent/PocketFlow支持DisChnPrunedLearner

[ICCV2017] Channel Pruning for Accelerating Very Deep Neural Networks
intro:Lasso回归
arxiv:https://arxiv.org/abs/1707.06168
github:https://github.com/yihui-he/channel-pruning

[ECCV2018] AMC: AutoML for Model Compression and Acceleration on Mobile Devices
intro:自动学习优化
arxiv:https://arxiv.org/abs/1802.03494
https://www.jiqizhixin.com/articles/AutoML-for-Model-Compression-and-Acceleration-on-Mobile-Devices论文翻译
github:https://github.com/Tencent/PocketFlow

[ICCV2017] Learning Efficient Convolutional Networks through Network Slimming
intro:Zhuang Liu
arxiv:https://arxiv.org/abs/1708.06519
github:https://github.com/Eric-mingjie/network-slimming
https://github.com/foolwood/pytorch-slimming

[ICLR2018] Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers

arxiv:https://arxiv.org/abs/1802.00124
github:[PyTorch]https://github.com/jack-willturner/batchnorm-pruning
[TensorFlow]https://github.com/bobye/batchnorm_prune

[CVPR2017] NISP: Pruning Networks using Neuron Importance Score Propagation

arxiv:https://arxiv.org/abs/1711.05908

[ICCV2017] ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression

web:http://lamda.nju.edu.cn/luojh/project/ThiNet_ICCV17/ThiNet_ICCV17_CN.html
github:https://github.com/Roll920/ThiNet
https://github.com/Roll920/ThiNet_Code

稀疏sparsity

SBNet: Sparse Blocks Network for Fast Inference
intro: Uber
arxiv:https://arxiv.org/abs/1801.02108
github:https://github.com/uber/sbnet

To Prune, or Not to Prune: Exploring the Efficacy of Pruning for Model Compression
intro:稀疏
arxiv:https://arxiv.org/abs/1710.01878
github:https://github.com/tensorflow/tensorflow/tree/master/tensorflow/contrib/model_pruning

Submanifold Sparse Convolutional Networks
intro:Facebook
arxiv:https://arxiv.org/abs/1706.01307
github:https://github.com/facebookresearch/SparseConvNet

融合fusion

蒸馏distillation

[NIPS2014] Distilling the Knowledge in a Neural Network
intro:Hinton出品
arxiv:https://arxiv.org/abs/1503.02531
github:https://github.com/peterliht/knowledge-distillation-pytorch

综合comprehensive

[ICLR2016] Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding
intro:开创先河
arxiv:https://arxiv.org/abs/1510.00149
github:https://github.com/songhan

Model Distillation with Knowledge Transfer from Face Classification to Alignment and Verification
intro:实验比较多，适合工程化
arxiv:https://arxiv.org/abs/1709.02929

持续更新中，欢迎关注

*延伸阅读