深度学习从入门到放弃之CV-Classification目录

个人认为,从难度上讲,先有image,再有Video。而image中,Classification应该是CV领域的最基础内容,基础到CV其他子领域都会用到的模型。下面是本人总结的Classification经典内容。相关arxiv都能下载到。


1998-LeNet----Gradient-based learning applied to document recognition

2012ILSVRC AlexNet----Imagenet classification with deep convolutional neural networks

2013ILSVRC ZFNet----Visualizing and Understanding Convolutional Networks

2014 AlexNet V2----One weird trick for parallelizing convolutional neural networks

2014----NiN----Network in Network

2014ILSVRC GoogLeNet(Inception V1)----Going deeper with convolutions_ILSVRC2014

2014ILSVRC VGGnet----Very deep convolutional networks for large-scale image recognition

2015 ILSVRC ResNet----Deep Residual Learning for Image Recognition

2015 inception v3----Rethinking the Inception Architecture for Computer Vision

2015----ReNet_A Recurrent Neural Network Based

2016----Binarized Neural Networks_Training Neural Networks with Weights and Activations Constrained to+ 1 or−1

2016----Identity Mappings in Deep Residual Networks

2016----Inception V4----Inception-ResNet and the Impact of Residual Connections on Learning

2016----Interleaved Group Convolutions for Deep Neural Networks

2016----Residual Networks are Exponential Ensembles of Relatively Shallow Networks

2016----SqueezeNet- AlexNet-level accuracy with 50x fewer parameters and 0.5MB model size

2016----Wide Residual Networks

2017---- FractalNet_Ultra-Deep Neural Networks without Residuals

2017---- Xception_Deep Learning with Depthwise Separable Convolutions

2017----An Analysis of Deep Neural Network Models for Practical Applications

2017----CVPR----ShuffleNet_An Extremely Efficient Convolutional Neural Network for Mobile Devices.

2017----CVPR2017 best paper----DenseNet ----Densely Connected Convolutional Networks

2017----ILSVRC2017 winner SENet----Squeeze-and-Excitation Networks

2017----Interleaved Group Convolutions for Deep Neural Networks

2017----Learning Transferable Architectures for Scalable Image Recognition

2017----Residual Attention Network for Image Classification

2017---- MobileNetV1_Efficient Convolutional Neural Networks for Mobile Vision Applications

2018----MobileNetV2----Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation


2018----MnasNet: Platform-Aware Neural Architecture Search for Mobile

Google 提出 MnasNet,使用强化学习的思路,提出一种资源约束的终端 CNN 模型的自动神经结构搜索方法。


返回CV总目录

编辑于 2018-08-20

文章被以下专栏收录