图像分类论文与代码大列表

【导读】图像分类作为计算机视觉的经典任务。一直被学者们研究探讨，本文介绍并比较了2014年以来较为出色的图像分类论文与代码

性能比较

为了简单，只列出在ImageNet上Top1 和 Top5 精度比较，准确度越高并不代表模型越好，因为一些网络是为了减小模型复杂度设计的。

论文与代码

VGG

Very Deep Convolutional Networks for Large-Scale Image Recognition.
Karen Simonyan, Andrew Zisserman

• pdf: https://arxiv.org/abs/1409.1556

• code:torchvision: https://github.com/pytorch/vision/blob/master/torchvision/models/vgg.py

• code:keras-applications :

  https://github.com/keras-team/keras-applications/blob/master/keras_applications/vgg16.py

• code: keras-applications : https://github.com/keras-team/keras-applications/blob/master/keras_applications/vgg19.py

GoogleNet

Going Deeper with Convolutions
Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich

• pdf: https://arxiv.org/abs/1409.4842

• code: unofficial-tensorflow :

  https://github.com/conan7882/GoogLeNet-Inception

• code: unofficial-caffe : https://github.com/lim0606/caffe-googlenet-bn

PReLU-nets

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun

• pdf: https://arxiv.org/abs/1502.01852

• code: unofficial-chainer : https://github.com/nutszebra/prelu_net

ResNet

Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun

• pdf: https://arxiv.org/abs/1512.03385

• code: facebook-torch : https://github.com/facebook/fb.resnet.torch

• code: torchvision : https://github.com/pytorch/vision/blob/master/torchvision/models/resnet.py

• code: keras-applications : https://github.com/keras-team/keras-applications/blob/master/keras_applications/resnet.py

• code: unofficial-keras : https://github.com/raghakot/keras-resnet

• code: unofficial-tensorflow : https://github.com/ry/tensorflow-resnet

PreActResNet

Identity Mappings in Deep Residual Networks
Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun

• pdf: https://arxiv.org/abs/1603.05027

• code: facebook-torch : https://github.com/facebook/fb.resnet.torch/blob/master/models/preresnet.lua

• code: official : https://github.com/KaimingHe/resnet-1k-layers

• code: unoffical-pytorch : https://github.com/kuangliu/pytorch-cifar/blob/master/models/preact_resnet.py

• code: unoffical-mxnet : https://github.com/tornadomeet/ResNet

Inceptionv3

Rethinking the Inception Architecture for Computer Vision
Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, Zbigniew Wojna

• pdf: https://arxiv.org/abs/1512.00567

• code: torchvision : https://github.com/pytorch/vision/blob/master/torchvision/models/inception.py

• code: keras-applications : https://github.com/keras-team/keras-applications/blob/master/keras_applications/inception_v3.py

Inceptionv4 && Inception-ResNetv2

Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke, Alex Alemi

• pdf: https://arxiv.org/abs/1602.07261

• code: unofficial-keras : https://github.com/kentsommer/keras-inceptionV4

• code: unofficial-keras : https://github.com/titu1994/Inception-v4

• code: unofficial-keras : https://github.com/yuyang-huang/keras-inception-resnet-v2

RiR

Resnet in Resnet: Generalizing Residual Architectures
Sasha Targ, Diogo Almeida, Kevin Lyman

• pdf: https://arxiv.org/abs/1603.08029

• code: unofficial-tensorflow : https://github.com/SunnerLi/RiR-Tensorflow

• code: unofficial-chainer : https://github.com/nutszebra/resnet_in_resnet

Stochastic Depth ResNet

Deep Networks with Stochastic Depth
Gao Huang, Yu Sun, Zhuang Liu, Daniel Sedra, Kilian Weinberger

• pdf: https://arxiv.org/abs/1603.09382

• code: unofficial-torch : https://github.com/yueatsprograms/Stochastic_Depth

• code: unofficial-chainer : https://github.com/yasunorikudo/chainer-ResDrop

• code: unofficial-keras : https://github.com/dblN/stochastic_depth_keras

WRN

Wide Residual Networks
Sergey Zagoruyko, Nikos Komodakis

• pdf: https://arxiv.org/abs/1605.07146

• code: official : https://github.com/szagoruyko/wide-residual-networks

• code: unofficial-pytorch : https://github.com/xternalz/WideResNet-pytorch

• code: unofficial-keras : https://github.com/asmith26/wide_resnets_keras

• code: unofficial-pytorch : https://github.com/meliketoy/wide-resnet.pytorch

squeezenet

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Forrest N. Iandola, Song Han, Matthew W. Moskewicz, Khalid Ashraf, William J. Dally, Kurt Keutzer

• pdf: https://arxiv.org/abs/1602.07360

• code: torchvision : https://github.com/pytorch/vision/blob/master/torchvision/models/squeezenet.py

• code: unofficial-caffe : https://github.com/DeepScale/SqueezeNet

• code: unofficial-keras : https://github.com/rcmalli/keras-squeezenet

• code: unofficial-caffe : https://github.com/songhan/SqueezeNet-Residual

GeNet

Genetic CNN
Lingxi Xie, Alan Yuille

• pdf: https://arxiv.org/abs/1703.01513

• code: unofficial-tensorflow : https://github.com/aqibsaeed/Genetic-CNN

MetaQNN

Designing Neural Network Architectures using Reinforcement Learning
Bowen Baker, Otkrist Gupta, Nikhil Naik, Ramesh Raskar

• pdf: https://arxiv.org/abs/1703.01513

• code: official : https://github.com/bowenbaker/metaqnn

PyramidNet

Deep Pyramidal Residual Networks
Dongyoon Han, Jiwhan Kim, Junmo Kim

• pdf: https://arxiv.org/abs/1610.02915

• code: official : https://github.com/jhkim89/PyramidNet

• code: unofficial-pytorch : https://github.com/dyhan0920/PyramidNet-PyTorch

DenseNet

Densely Connected Convolutional Networks
Gao Huang, Zhuang Liu, Laurens van der Maaten, Kilian Q. Weinberger

• pdf: https://arxiv.org/abs/1608.06993

• code: official : https://github.com/liuzhuang13/DenseNet

• code: unofficial-keras : https://github.com/titu1994/DenseNet

• code: unofficial-caffe : https://github.com/shicai/DenseNet-Caffe

• code: unofficial-tensorflow : https://github.com/YixuanLi/densenet-tensorflow

• code: unofficial-pytorch : https://github.com/YixuanLi/densenet-tensorflow

• code: unofficial-pytorch : https://github.com/bamos/densenet.pytorch

• code: unofficial-keras : https://github.com/flyyufelix/DenseNet-Keras

FractalNet

FractalNet: Ultra-Deep Neural Networks without Residuals
Gustav Larsson, Michael Maire, Gregory Shakhnarovich

• pdf: https://arxiv.org/abs/1605.07648

• code: unofficial-caffe : https://github.com/gustavla/fractalnet

• code: unofficial-keras : https://github.com/snf/keras-fractalnet

• code: unofficial-tensorflow : https://github.com/tensorpro/FractalNet

ResNext

Aggregated Residual Transformations for Deep Neural Networks
Saining Xie, Ross Girshick, Piotr Dollár, Zhuowen Tu, Kaiming He

• pdf: https://arxiv.org/abs/1611.05431

• code: official : https://github.com/facebookresearch/ResNeXt

• code: keras-applications : https://github.com/keras-team/keras-applications/blob/master/keras_applications/resnext.py

• code: unofficial-pytorch : https://github.com/prlz77/ResNeXt.pytorch

• code: unofficial-keras : https://github.com/titu1994/Keras-ResNeXt

• code: unofficial-tensorflow : https://github.com/taki0112/ResNeXt-Tensorflow

• code: unofficial-tensorflow : https://github.com/wenxinxu/ResNeXt-in-tensorflow

IGCV1

Interleaved Group Convolutions for Deep Neural Networks
Ting Zhang, Guo-Jun Qi, Bin Xiao, Jingdong Wang

• pdf: https://arxiv.org/abs/1707.02725

• code official : https://github.com/hellozting/InterleavedGroupConvolutions

Residual Attention Network

Residual Attention Network for Image Classification
Fei Wang, Mengqing Jiang, Chen Qian, Shuo Yang, Cheng Li, Honggang Zhang, Xiaogang Wang, Xiaoou Tang

• pdf: https://arxiv.org/abs/1704.06904

• code: official : https://github.com/fwang91/residual-attention-network

• code: unofficial-pytorch : https://github.com/tengshaofeng/ResidualAttentionNetwork-pytorch

• code: unofficial-gluon : https://github.com/PistonY/ResidualAttentionNetwork

• code: unofficial-keras : https://github.com/koichiro11/residual-attention-network

Xception

Xception: Deep Learning with Depthwise Separable Convolutions
François Chollet

• pdf: https://arxiv.org/abs/1610.02357

• code: unofficial-pytorch : https://github.com/jfzhang95/pytorch-deeplab-xception/blob/master/modeling/backbone/xception.py

• code: unofficial-tensorflow : https://github.com/kwotsin/TensorFlow-Xception

• code: unofficial-caffe : https://github.com/yihui-he/Xception-caffe

• code: unofficial-pytorch : https://github.com/tstandley/Xception-PyTorch

• code: keras-applications : https://github.com/keras-team/keras-applications/blob/master/keras_applications/xception.py

MobileNet

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, Hartwig Adam

• pdf: https://arxiv.org/abs/1704.04861

• code: unofficial-tensorflow : https://github.com/Zehaos/MobileNet

• code: unofficial-caffe : https://github.com/shicai/MobileNet-Caffe

• code: unofficial-pytorch : https://github.com/marvis/pytorch-mobilenet

• code: keras-applications : https://github.com/keras-team/keras-applications/blob/master/keras_applications/mobilenet.py

PolyNet

PolyNet: A Pursuit of Structural Diversity in Very Deep Networks
Xingcheng Zhang, Zhizhong Li, Chen Change Loy, Dahua Lin

• pdf: https://arxiv.org/abs/1611.05725

• code: official : https://github.com/open-mmlab/polynet

DPN

Dual Path Networks
Yunpeng Chen, Jianan Li, Huaxin Xiao, Xiaojie Jin, Shuicheng Yan, Jiashi Feng

• pdf: https://arxiv.org/abs/1707.01629

• code: official : https://github.com/cypw/DPNs

• code: unoffical-keras : https://github.com/titu1994/Keras-DualPathNetworks

• code: unofficial-pytorch : https://github.com/oyam/pytorch-DPNs

• code: unofficial-pytorch : https://github.com/rwightman/pytorch-dpn-pretrained

Block-QNN

Practical Block-wise Neural Network Architecture Generation
Zhao Zhong, Junjie Yan, Wei Wu, Jing Shao, Cheng-Lin Liu

• pdf: https://arxiv.org/abs/1708.05552

CRU-Net

Sharing Residual Units Through Collective Tensor Factorization in Deep Neural Networks
Chen Yunpeng, Jin Xiaojie, Kang Bingyi, Feng Jiashi, Yan Shuicheng

• pdfhttps://arxiv.org/abs/1703.02180

• code official : https://github.com/cypw/CRU-Net

• code unofficial-mxnet : https://github.com/bruinxiong/Modified-CRUNet-and-Residual-Attention-Network.mxnet

ShuffleNet

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
Xiangyu Zhang, Xinyu Zhou, Mengxiao Lin, Jian Sun

• pdf: https://arxiv.org/abs/1707.01083

• code: unofficial-tensorflow : https://github.com/MG2033/ShuffleNet

• code: unofficial-pytorch : https://github.com/jaxony/ShuffleNet

• code: unofficial-caffe : https://github.com/farmingyard/ShuffleNet

• code: unofficial-keras : https://github.com/scheckmedia/keras-shufflenet

CondenseNet

CondenseNet An Efficient DenseNet using Learned Group Convolutions
Gao Huang, Shichen Liu, Laurens van der Maaten, Kilian Q. Weinberger

• pdf: https://arxiv.org/abs/1711.09224

• code: official : https://github.com/ShichenLiu/CondenseNet

• code: unofficial-tensorflow : https://github.com/markdtw/condensenet-tensorflow

NasNet

Learning Transferable Architectures for Scalable Image Recognition
Barret Zoph, Vijay Vasudevan, Jonathon Shlens, Quoc V. Le

• pdf: https://arxiv.org/abs/1707.07012

• code: unofficial-keras : https://github.com/titu1994/Keras-NASNet

• code: keras-applications : https://github.com/keras-team/keras-applications/blob/master/keras_applications/nasnet.py

• code: unofficial-pytorch : https://github.com/wandering007/nasnet-pytorch

• code: unofficial-tensorflow : https://github.com/yeephycho/nasnet-tensorflow

MobileNetV2

MobileNetV2: Inverted Residuals and Linear Bottlenecks
Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen

• pdf: https://arxiv.org/abs/1801.04381

• code: unofficial-keras : https://github.com/xiaochus/MobileNetV2

• code: unofficial-pytorch : https://github.com/Randl/MobileNetV2-pytorch

• code: unofficial-tensorflow : https://github.com/neuleaf/MobileNetV2

IGCV2

IGCV2: Interleaved Structured Sparse Convolutional Neural Networks
Guotian Xie, Jingdong Wang, Ting Zhang, Jianhuang Lai, Richang Hong, Guo-Jun Qi

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

hier

Hierarchical Representations for Efficient Architecture Search
Hanxiao Liu, Karen Simonyan, Oriol Vinyals, Chrisantha Fernando, Koray Kavukcuoglu

• pdf: https://arxiv.org/abs/1711.00436

PNasNet

Progressive Neural Architecture Search
Chenxi Liu, Barret Zoph, Maxim Neumann, Jonathon Shlens, Wei Hua, Li-Jia Li, Li Fei-Fei, Alan Yuille, Jonathan Huang, Kevin Murphy

• pdf: https://arxiv.org/abs/1712.00559

• code: tensorflow-slim : https://github.com/tensorflow/models/blob/master/research/slim/nets/nasnet/pnasnet.py

• code: unofficial-pytorch : https://github.com/chenxi116/PNASNet.pytorch

• code: unofficial-tensorflow : https://github.com/chenxi116/PNASNet.TF

AmoebaNet

Regularized Evolution for Image Classifier Architecture Search
Esteban Real, Alok Aggarwal, Yanping Huang, Quoc V Le

• pdf: https://arxiv.org/abs/1802.01548

• code: tensorflow-tpu : https://github.com/tensorflow/tpu/tree/master/models/official/amoeba_net

SENet

Squeeze-and-Excitation Networks
Jie Hu, Li Shen, Samuel Albanie, Gang Sun, Enhua Wu

• pdf: https://arxiv.org/abs/1709.01507

• code: official : https://github.com/hujie-frank/SENet

• code: unofficial-pytorch : https://github.com/moskomule/senet.pytorch

• code: unofficial-tensorflow : https://github.com/taki0112/SENet-Tensorflow

• code: unofficial-caffe : https://github.com/shicai/SENet-Caffe

• code: unofficial-mxnet : https://github.com/bruinxiong/SENet.mxnet

ShuffleNetV2

ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
Ningning Ma, Xiangyu Zhang, Hai-Tao Zheng, Jian Sun

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

• code: unofficial-pytorch :https://github.com/Randl/ShuffleNetV2-pytorch

• code: unofficial-keras : https://github.com/opconty/keras-shufflenetV2

• code:unofficial-pytorch : https://github.com/Bugdragon/ShuffleNet_v2_PyTorch

• code: unofficial-caff2: https://github.com/wolegechu/ShuffleNetV2.Caffe2

IGCV3

IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural Networks
Ke Sun, Mingjie Li, Dong Liu, Jingdong Wang

• pdf: https://arxiv.org/abs/1806.00178

• code: official : https://github.com/homles11/IGCV3

• code: unofficial-pytorch : https://github.com/xxradon/IGCV3-pytorch

• code: unofficial-tensorflow : https://github.com/ZHANG-SHI-CHANG/IGCV3

MNasNet

MnasNet: Platform-Aware Neural Architecture Search for Mobile
Mingxing Tan, Bo Chen, Ruoming Pang, Vijay Vasudevan, Quoc V. Le

• pdf: https://arxiv.org/abs/1807.11626

• code: unofficial-pytorch : https://github.com/AnjieZheng/MnasNet-PyTorch

• code: unofficial-caffe : https://github.com/LiJianfei06/MnasNet-caffe

• code: unofficial-MxNet : https://github.com/chinakook/Mnasnet.MXNet

• code: unofficial-keras : https://github.com/Shathe/MNasNet-Keras-Tensorflow

Github 地址：

https://github.com/weiaicunzai/awesome-image-classification

-END-

专 · 知

专知《深度学习:算法到实战》课程全部完成！480+位同学在学习，现在报名，限时优惠！网易云课堂人工智能畅销榜首位！

请加专知小助手微信（扫一扫如下二维码添加），咨询《深度学习:算法到实战》参团限时优惠报名~

欢迎微信扫一扫加入专知人工智能知识星球群，获取专业知识教程视频资料和与专家交流咨询！

请PC登录www.zhuanzhi.ai或者点击阅读原文，注册登录专知，获取更多AI知识资料！

点击“阅读原文”，了解报名专知《深度学习:算法到实战》课程