1.LeNet-5

论文《Gradient-based learning applied to document recognition》 
web：http://yann.lecun.com/exdb/lenet/ 

2.AlexNet

论文《ImageNet Classification with Deep Convolutional Neural Networks》 

 

3.ZFNet

论文《Visualizing and Understanding Convolutional Networks》 
arxiv：https://arxiv.org/abs/1311.2901 

4.Network In Network

论文《Network In Network》 
 

5.VGG

论文《Very Deep Convolutional Networks for Large-Scale Image Recognition》 
web：http://www.robots.ox.ac.uk/~vgg/research/very_deep/ 
slides：http://www.robots.ox.ac.uk/~karen/pdf/ILSVRC_2014.pdf 

 

6.GoogLeNet(Inception V1)

论文《Going Deeper with Convolutions》 
arxiv：https://arxiv.org/abs/1409.4842 

      

7.Inception V2

论文《Batch Normalization：Accelerating Deep Network Training by Reducing Internal Covariate Shift》  

 

8.Inception V3

论文《Rethinking the Inception Architecture for Computer Vision》 
arxiv：https://arxiv.org/abs/1512.00567

一个5×5的卷积核可以由2次3×3的卷积代替 

 

一个3×3的卷积核可以由1×3和3×1的卷积代替 

原始Inception结构 

把5×5的卷积由2次3×3的卷积代替后的Inception结构 

把n×n的卷积由1×n和n×1的卷积代替后的Inception结构 

9.Inception V4，Inception-ResNet

论文《Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning》 
arxiv：https://arxiv.org/abs/1602.07261

Inception-v4

Stem 

Inception-A 

Reduction-A 

Inception-B 

Reduction-B 

Inception-C 

Inception-ResNet-v1

Inception-ResNet-v2

10.ResNet

论文《Deep Residual Learning for Image Recognition》 
arxiv：https://arxiv.org/abs/1512.03385 

11.SqueezeNet

论文《SqueezeNet：AlexNet-level accuracy with 50x fewer parameters and 0.5MB model size》 

12.DenseNet

论文《Densely Connected Convolutional Networks》 
arxiv：https://arxiv.org/abs/1608.06993 
 

13.Xception 

论文《Xception: Deep Learning with Depthwise Separable Convolutions》 
arxiv：https://arxiv.org/abs/1610.02357 

14.ResNeXt

论文《Aggregated Residual Transformations for Deep Neural Networks》 
arxiv：https://arxiv.org/abs/1611.05431 

15.PolyNet

论文《PolyNet: A Pursuit of Structural Diversity in Very Deep Networks》 
arxiv：https://arxiv.org/abs/1611.05431 
 

16.MobileNet

论文《MobileNets：Efficient Convolutional Neural Networks for Mobile Vision Applications》 
 

17.ShuffleNet

论文《ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices》 

18.DPN

论文《Dual Path Networks》 
arxiv：https://arxiv.org/abs/1707.01629 
 

19.NASNet

论文《Learning transferable architectures for scalable image recognition》 

20.SENet

论文《Squeeze-and-Excitation Networks》 

 

21.MobileNet v2

论文《Inverted Residuals and Linear Bottlenecks：Mobile Networks for Classification, Detection and Segmentation》