[Paper List] 卷積神經網路 (CNN)

卷積神經網路 (Convolutional Neural Network; CNN)

LeNet
Title: Gradient-based learning applied to document recognition
Authors: LeCun, Yann and Bottou, L{\'e}on and Bengio, Yoshua and Haffner, Patrick and others
Source: Proceedings of the IEEE
Year: 1998

AlexNet
Title: Imagenet classification with deep convolutional neural networks
Authors: Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E
Source: Advances in neural information processing systems
Year: 2012

VGG
Title: Very deep convolutional networks for large-scale image recognition
Authors: Simonyan, Karen and Zisserman, Andrew
Source: arXiv
Year: 2014

Inception V1
Title: Going deeper with convolutions
Authors: Szegedy, Christian and Liu, Wei and Jia, Yangqing and Sermanet, Pierre and Reed, Scott and Anguelov, Dragomir and Erhan, Dumitru and Vanhoucke, Vincent and Rabinovich, Andrew
Source: Proceedings of the IEEE conference on computer vision and pattern recognition
Year: 2015

Inception V2
Title: Batch normalization: Accelerating deep network training by reducing internal covariate shift
Authors: Ioffe, Sergey and Szegedy, Christian
Source: arXiv
Year: 2015

Inception V3
Title: Rethinking the inception architecture for computer vision
Authors: Szegedy, Christian and Vanhoucke, Vincent and Ioffe, Sergey and Shlens, Jon and Wojna, Zbigniew
Source: Proceedings of the IEEE conference on computer vision and pattern recognition
Year: 2016

Inception V4
Title: Inception-v4, inception-resnet and the impact of residual connections on learning
Authors: Szegedy, Christian and Ioffe, Sergey and Vanhoucke, Vincent and Alemi, Alexander A
Source: Thirty-First AAAI Conference on Artificial Intelligence
Year: 2017

ResNet
Title: Deep residual learning for image recognition
Authors: He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian
Source: Proceedings of the IEEE conference on computer vision and pattern recognition
Year: 2016

ResNext
Title: Aggregated residual transformations for deep neural networks
Authors: Xie, Saining and Girshick, Ross and Doll{\'a}r, Piotr and Tu, Zhuowen and He, Kaiming
Source: Proceedings of the IEEE conference on computer vision and pattern recognition
Year: 2017

AllConvNet
Title: Striving for simplicity: The all convolutional net
Authors: Springenberg, Jost Tobias and Dosovitskiy, Alexey and Brox, Thomas and Riedmiller, Martin
Source: arXiv
Year: 2014

DenseNet
Title: Densely connected convolutional networks
Authors: Huang, Gao and Liu, Zhuang and Van Der Maaten, Laurens and Weinberger, Kilian Q
Source: Proceedings of the IEEE conference on computer vision and pattern recognition
Year: 2017

EfficientNet

Title: Efficientnet: Rethinking model scaling for convolutional neural networks

Authors: Tan, Mingxing and Le, Quoc V

Source: arXiv

Year: 2019

Noisy Student

Title: Self-training with Noisy Student improves ImageNet classification

Authors: Xie, Qizhe and Hovy, Eduard and Luong, Minh-Thang and Le, Quoc V

Source: arXiv

Year: 2019

輕量化卷積神經網路 (Light-Weight CNN)

MobileNets
Title: Mobilenets: Efficient convolutional neural networks for mobile vision applications
Authors: Howard, Andrew G and Zhu, Menglong and Chen, Bo and Kalenichenko, Dmitry and Wang, Weijun and Weyand, Tobias and Andreetto, Marco and Adam, Hartwig
Source: arXiv
Year: 2017

ShuffleNet
Title: Shufflenet: An extremely efficient convolutional neural network for mobile devices
Authors: Zhang, Xiangyu and Zhou, Xinyu and Lin, Mengxiao and Sun, Jian
Source: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
Year: 2018

CondenseNet
Title: Condensenet: An efficient densenet using learned group convolutions
Authors: Huang, Gao and Liu, Shichen and Van der Maaten, Laurens and Weinberger, Kilian Q
Source: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
Year: 2018

神經網路量化 (Quantization)

Quantization
Title: Quantization and training of neural networks for efficient integer-arithmetic-only inference
Authors: Jacob, Benoit and Kligys, Skirmantas and Chen, Bo and Zhu, Menglong and Tang, Matthew and Howard, Andrew and Adam, Hartwig and Kalenichenko, Dmitry
Source: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
Year: 2018

TWN
Title: Ternary weight networks
Authors: Li, Fengfu and Zhang, Bo and Liu, Bin
Source: arXiv preprint arXiv:1605.04711
Year: 2016

Notes: weights are quantized to +1/0/-1

XNORNet
Title: Xnor-net: Imagenet classification using binary convolutional neural networks
Authors: Rastegari, Mohammad and Ordonez, Vicente and Redmon, Joseph and Farhadi, Ali
Source: European Conference on Computer Vision
Year: 2016

Notes: weights are quantized to +1/-1

Do-Re-Fa Net

Title: Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients

Authors: Zhou, Shuchang and Wu, Yuxin and Ni, Zekun and Zhou, Xinyu and Wen, He and Zou, Yuheng

Source: arXiv preprint arXiv:1606.06160

Year: 2016

Notes: quantize both forward and backward path

WAGE

Title: Training and inference with integers in deep neural networks

Authors: Wu, Shuang and Li, Guoqi and Chen, Feng and Shi, Luping

Source: arXiv preprint arXiv:1802.04680

Year: 2018

Notes: quantize both forward and backward path