视觉注意力机制的发展历程-Attention-Family

目录

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在这里插入图片描述
----------------------------------------------------------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:
在这里插入图片描述

---------------------------------2015-------------------------------------

Spatial Transformer Networks(NIPS)

论文下载:paper-Spatial Transformer Networks
论文解读:Spatial Transformer Networks
代码下载:github-Spatial Transformer Networks

---------------------------------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

Residual Attention Network for Image Classification

论文下载:paper-Residual Attention Network for Image Classification
论文解读:Residual Attention Network for Image Classification
代码下载:1-Residual Attention Network for Image Classification

代码下载:2-Residual Attention Network for Image Classification

---------------------------------2018-------------------------------------

GAN: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

NLNet:Compact Generalized Non-local Network

论文下载:Compact Generalized Non-local Network

BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation(ECCV)

论文下载:BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
论文解读:BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
代码下载:BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation

评论 3
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值