[Paper Review] CNN-based Image Classification
1.[2011 NIPS] (AlexNet) ImageNet Classification with Deep Convolutional Neural Networks
Introduction
2.[2014 arXiv] (VGGNet) VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION
author : Karen Simonyan & Andrew Zisserman+Visual Geometry Group, Department of Engineering Science, University of Oxford {karen,az}@robots.ox.ac.uk
3.[2014 ICLR] Network In Network
우리는Network In Network(NIN)이라고 불리는 새로운 deep network structure를 제안한다.우리는 receptive field에 대한 data를 더욱 abstract하는 complex structure로 micro neural network
4.[2015 CVPR] (GoogleNet) Going deeper with convolutions
Abstract 1. Introduction 2. Related Work 3. Motivation and High Level Consideration 4. Architectural Details 5. GoogleNet 6. Training Methodolog
5.[2015 ICML] Batch Normalization : Accelerating Deep Network Training by Reducing Internal Covariate Shift
Author : Sergey Ioffe, Christian SzegedyConference : ICML 2015(International Conference on Machine Learning)
6.[2016 CVPR] (ResNet) Deep Residual Learning for Image Recognition
authors : Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun학회 : Computer Vision and Pattern Recognition (cs.CV)https://arxiv.org/abs/1512.03385De
7.[2018 CVPR] MobileNetV2: Inverted Residuals and Linear Bottlenecks, Sandler
author : Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh ChenSubjects : The IEEE Conference on Computer Vision and Pattern Re
8.[2018 ECCV] [Simple Review] CBAM: Convolutional Block Attention Module
당시에 network engineering methods는 주로 depth, width, and cardinality를 focus했는데,우리는 attention을 focus함.attention은 실제로 one of the curious facets of a human
9.[2018 CVPR] [Simple Review] Squeeze-and-Excitation Networks
Squeeze: Global Information Embedding한 channel의 global spatial information을 a channel descriptor로 squeeze한다.global average pooling을 사용하여 channel-wise