8.16模型整理

文章目录

• [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation(ECCV2018)](#Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation(ECCV2018))
• • 方法
• [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning（2016）](#Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning（2016）)
• • 方法
• [Wide Residual Networks（2017）](#Wide Residual Networks（2017）)
• • 方法
• [mixup: Beyond Empirical Risk Minimization（ICLR2018）](#mixup: Beyond Empirical Risk Minimization（ICLR2018）)
• • 方法
• [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](#Swin Transformer: Hierarchical Vision Transformer using Shifted Windows)
• • 方法
• [Pyramid Scene Parsing Network（2017）](#Pyramid Scene Parsing Network（2017）)
• [Searching for MobileNetV3（2019）](#Searching for MobileNetV3（2019）)
• • 方法
• [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size（2016）](#SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size（2016）)
• • 方法
• [Identity Mappings in Deep Residual Networks（2016）](#Identity Mappings in Deep Residual Networks（2016）)
• • 方法
• [Aggregated Residual Transformations for Deep Neural Networks](#Aggregated Residual Transformations for Deep Neural Networks)
• • 方法
• [MLP-Mixer: An all-MLP Architecture for Vision（2021）](#MLP-Mixer: An all-MLP Architecture for Vision（2021）)
• [MOCO：Momentum Contrast for Unsupervised Visual Representation Learning](#MOCO：Momentum Contrast for Unsupervised Visual Representation Learning)
• [A ConvNet for the 2020s](#A ConvNet for the 2020s)
• [MAE：Masked Autoencoders Are Scalable Vision Learners](#MAE：Masked Autoencoders Are Scalable Vision Learners)
• [Xception: Deep Learning with Depthwise Separable Convolutions](#Xception: Deep Learning with Depthwise Separable Convolutions)
• • 方法
• [CLIP：Learning Transferable Visual Models From Natural Language Supervision](#CLIP：Learning Transferable Visual Models From Natural Language Supervision)
• • 方法
• [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](#ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices)
• • 方法
• [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](#ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design)
• • 方法
• [ResNeSt: Split-Attention Networks](#ResNeSt: Split-Attention Networks)
• • 本文方法

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation(ECCV2018)

方法

代码地址

DeepLabV3+结构

Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning（2016）

方法

Wide Residual Networks（2017）

方法

代码地址

我感觉是没啥变化

mixup: Beyond Empirical Risk Minimization（ICLR2018）

方法

主要看代码里面得lam和alpha

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

方法

Vit的滑动窗口版本

Pyramid Scene Parsing Network（2017）

Searching for MobileNetV3（2019）

方法

这是一篇关于网络架构搜索的文章

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

方法

Identity Mappings in Deep Residual Networks（2016）

方法

讲了各种各样的跳跃连接分析

Aggregated Residual Transformations for Deep Neural Networks

方法

相当于就是参数减少

MLP-Mixer: An all-MLP Architecture for Vision（2021）

token混合和channel混合

MOCO：Momentum Contrast for Unsupervised Visual Representation Learning

采用不同存储结构，moco采用的是队列

A ConvNet for the 2020s

做到极致的卷积

MAE：Masked Autoencoders Are Scalable Vision Learners

类似于bert，预测mask部分，自监督学习

Xception: Deep Learning with Depthwise Separable Convolutions

方法

CLIP：Learning Transferable Visual Models From Natural Language Supervision

方法

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

方法

分组卷积并混合

ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

方法

ResNeSt: Split-Attention Networks

本文方法