Attention-Family

The development of attention mechanisms

视觉注意力机制的发展历程-Attention-Family

今天笔者发神经想记录一下视觉注意力机制的发展历程

-------------------attention主要的发展路径及目前的主流方法----------------

自从Attention 机制继在 NLP 领域不错的效果之后，Attention 机制也在 CV 领域迅速拉开了大幕。以 Kaiming He 组的 Nonlocal为起点，迅速开启了Attention 时代。此后层出不穷的文章，犹如雨后春笋般开遍了整个CV领域。
下面以时间线为轴记录视觉注意力机制的发展论文以及代码：

————————————2016—————————————

Attention to Scale-Scale-aware Semantic Image Segmentation(CVPR)

论文下载：paper-Attention to Scale-Scale-aware Semantic Image Segmentation
论文解读：Attention to Scale-Scale-aware Semantic Image Segmentation
代码下载：————————————————————————————

————————————2017—————————————

Attention Is All You Need

论文下载：Attention Is All You Need

Semi-Supervised Classification with Graph Convolutional Networks(ICLR)

论文下载：Semi-Supervised Classification with Graph Convolutional Networks

————————————2018—————————————

Graph Attention Networks

论文下载：Graph Attention Networks
论文代码：Graph Attention Networks

Graph-Based Global Reasoning Networks

论文下载：paper-Graph-Based Global Reasoning Networks
论文解读：Graph-Based Global Reasoning Networks

Compact Generalized Non-local Network

论文下载：Compact Generalized Non-local Network

EncNet-Context Encoding for Semantic Segmentation(CVPR)

论文下载：paper-Context Encoding for Semantic Segmentation
论文解读：EncNet-Context Encoding for Semantic Segmentation
代码下载：pytorch-Context Encoding for Semantic Segmentation

DFN-Learning a Discriminative Feature Network for Semantic Segmentation(CVPR)

论文下载：paper-Learning a Discriminative Feature Network for Semantic Segmentation
论文解读：DFN-Learning a Discriminative Feature Network for Semantic Segmentation
代码下载：keras--Learning a Discriminative Feature Network for Semantic Segmentation

PSANet- Point-wise Spatial Attention Network for Scene Parsing(ECCV)

论文下载：paper-Point-wise Spatial Attention Network for Scene Parsing
论文解读：PSANet-Point-wise Spatial Attention Network for Scene Parsing
代码下载：pytorch-Point-wise Spatial Attention Network for Scene Parsing

SENet-Squeeze-and-Excitation Networks(CVPR)

论文下载：paper-Squeeze-and-Excitation Networks
论文解读：SENet-Squeeze-and-Excitation Networks
代码下载：pytorch-Squeeze-and-Excitation Networks

A^2-Nets- Double Attention Networks(NIPS)

论文下载：paper-A^2-Nets- Double Attention Networks
论文解读：A^2-Nets- Double Attention Networks
代码下载：pytorch-A^2-Nets- Double Attention Networks

BAM: Bottleneck Attention Module(BMVC)

论文下载：paper-Bottleneck Attention Module
论文解读：BAM: Bottleneck Attention Module
代码下载：pytorch-Bottleneck Attention Module

CBAM-Convolutional Block Attention Module

论文下载：paper-Convolutional Block Attention Module
论文解读：CBAM-Convolutional Block Attention Module
代码下载：pytorch-Convolutional Block Attention Module

Non-local Neural Networks(CVPR)

论文下载：paper-Non-local Neural Networks
论文解读：Non-local Neural Networks
代码下载：keras-Non-local Neural Networks
---------------pytorch-Non-local Neural Networks

————————————2019—————————————

DANet-Dual Attention Network for Scene Segmentation(CVPR)

论文下载：paper-Dual Attention Network for Scene Segmentation
论文解读：DANet-Dual Attention Network for Scene Segmentation
代码下载：pytorch-Dual Attention Network for Scene Segmentation

OCNet: Object Context Network for Scene Parsing(ECCV)

论文下载：paper-Object Context Network for Scene Parsing
代码解读：OCNet: Object Context Network for Scene Parsing
代码下载：pytorch- Object Context Network for Scene Parsing

ACNet- Attention Based Network to Exploit Complementary Features for RGBD Semantic Segmentation(ICIP)

论文下载：paper- Attention Based Network to Exploit Complementary Features for RGBD Semantic Segmentation
论文解读：ACNet-Attention Based Network to Exploit Complementary Features for RGBD Semantic Segmentation
代码下载：pytorch-Attention Based Network to Exploit Complementary Features for RGBD Semantic Segmentation

EMANet-Expectation-Maximization Attention Networks for Semantic Segmentation (ICCV)

论文下载：paper-Expectation-Maximization Attention Networks for Semantic Segmentation
论文解读：EMANet-Expectation-Maximization Attention Networks for Semantic Segmentation
代码下载：EMANet-Expectation-Maximization Attention Networks for Semantic Segmentation

APCNet-Adaptive Pyramid Context Network for Semantic Segmentation(CVPR)

论文下载：paper-Adaptive Pyramid Context Network for Semantic Segmentation
论文解读：APCNet-Adaptive Pyramid Context Network for Semantic Segmentation
代码下载：———————————————————————————————

LatentGNN: Learning Efficient Non-local Relations for Visual Recognition

论文下载：LatentGNN: Learning Efficient Non-local Relations for Visual Recognition

An Empirical Study of Spatial Attention Mechanisms in Deep Networks

论文下载：An Empirical Study of Spatial Attention Mechanisms in Deep Networks

Feature Denoising for Improving Adversarial Robustness

论文下载：Feature Denoising for Improving Adversarial Robustness
论文解读： Feature Denoising for Improving Adversarial Robustness
代码下载： Feature Denoising for Improving Adversarial Robustness

Interlaced Sparse Self-Attention for Semantic Segmentation

论文下载：Interlaced Sparse Self-Attention for Semantic Segmentation

Interleaved Group Convolutions for Deep Neural Networks

论文下载：Interleaved Group Convolutions for Deep Neural Networks

Dynamic Graph Message Passing Networks

论文下载：Dynamic Graph Message Passing Networks

A General Framework for Bilateral and Mean Shift Filtering

论文下载：A General Framework for Bilateral and Mean Shift Filtering

CARAFE: Content-Aware ReAssembly of FEatures

论文下载： CARAFE: Content-Aware ReAssembly of FEatures

Expectation Maximization Attention Networks for Semantic Segmentation

论文下载：Expectation Maximization Attention Networks for Semantic Segmentation

————————————2020—————————————

SANet-Squeeze-and-Attention Networks for Semantic Segmentation(CVPR)

论文下载：paper-Squeeze-and-Attention Networks for Semantic Segmentation
代码解读：SANet-Squeeze-and-Attention Networks for Semantic Segmentation
代码下载：———————————————————————————————