[Paper Reading] Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
论文链接:https://arxiv.org/pdf/1502.03044.pdf
代码链接:https://github.com/kelvinxu/arctic-captions & https://github.com/yunjey/show-attend-and-tell & https://github.com/jazzsaxmafia/show_attend_and_tell.tensorflow
主要贡献
在这篇文章中,作者将“注意力机制(Attention Mechanism)”引入了神经机器翻译(Neural Image Captioning)领域,提出了两种不同的注意力机制:‘Soft’ Deterministic Attention Mechanism & ‘Hard’ Stochastic Attention Mechanism。下图展示了"Show, Attend and Tell"模型的整体框架。

注意力机制的关键点在于,如何从图像的特征向量ai中计算得到上下文向量zt。对于每一个位置i,注意力机制能够产生一个权重eti。在Hard Attention机制中,权重αti所扮演的角色是图像区域向量ai在t时刻被选中作为解码器的信息的概率,有且只有一个区域会被选中,为此,引入变量st,i,当区域i被选中时为1,否则为0;在Soft Attention机制中,权重αti所扮演的角色是图像区域向量ai在t时刻输入解码器的信息中所占的比例。(参考Attention机制论文阅读——Soft和Hard Attention,Multimodal —— 看图说话(Image Caption)任务的论文笔记(二)引入attention机制)
实验细节
- 在文章中,作者提出使用在ImageNet数据集上预训练好、不进行微调的VGGNet提取图像特征,将block5_conv4(Conv2D)提取到的feature map(14×14×512)reshape为196×512(L×D,L=196,D=512,即196个图像区域,每个区域特征向量的维度是512)的图像区域向量ai。
To create the annotations ai used by our decoder, we used the Oxford VGGnet pretrained on ImageNet without finetuning.
In our experiments we use the 14×14×512 feature map of the fourth convolutional layer before max pooling. This means our decoder operates on the flattened 196×512 (i.e L × D) encoding.
- 在文章中,作者指出,解码器LSTM初始的细胞状态(init_c)与隐层状态(init_h)由从图像中提取到的特征向量及两个独立的多层感知机(Multi-Layer Perception, MLP)决定。
The initial memory state and hidden state of the LSTM are predicted by an average of the annotation vectors fed through two separate MLPs(init,c and init,h).
版权声明:本文为博主原创文章,欢迎转载,转载请注明作者及原文出处!
[Paper Reading] Show, Attend and Tell: Neural Image Caption Generation with Visual Attention的更多相关文章
- Paper Reading - Show, Attend and Tell: Neural Image Caption Generation with Visual Attention ( ICML 2015 )
Link of the Paper: https://arxiv.org/pdf/1502.03044.pdf Main Points: Encoder-Decoder Framework: Enco ...
- 论文笔记:Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention 2018-08-10 10:15:06 Pap ...
- 论文:Show, Attend and Tell: Neural Image Caption Generation with Visual Attention-阅读总结
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention-阅读总结 笔记不能简单的抄写文中的内容,得有自 ...
- Paper Reading - Show and Tell: A Neural Image Caption Generator ( CVPR 2015 )
Link of the Paper: https://arxiv.org/abs/1411.4555 Main Points: A generative model ( NIC, GoogLeNet ...
- [Paper Reading] Show and Tell: A Neural Image Caption Generator
论文链接:https://arxiv.org/pdf/1411.4555.pdf 代码链接:https://github.com/karpathy/neuraltalk & https://g ...
- [Paper Reading] Image Captioning using Deep Neural Architectures (arXiv: 1801.05568v1)
Main Contributions: A brief introduction about two different methods (retrieval based method and gen ...
- Paper Reading - CNN+CNN: Convolutional Decoders for Image Captioning
Link of the Paper: https://arxiv.org/abs/1805.09019 Innovations: The authors propose a CNN + CNN fra ...
- Paper Reading: Stereo DSO
开篇第一篇就写一个paper reading吧,用markdown+vim写东西切换中英文挺麻烦的,有些就偷懒都用英文写了. Stereo DSO: Large-Scale Direct Sparse ...
- Paper Reading - Mind’s Eye: A Recurrent Visual Representation for Image Caption Generation ( CVPR 2015 )
Link of the Paper: https://ieeexplore.ieee.org/document/7298856/ A Correlative Paper: Learning a Rec ...
随机推荐
- 5 webpack-dev-server的常用命令参数--open --port 3000 --contentBase src --hot
--open 自动打开浏览器 --port 3000 指定端口3000 --contentBase src 内容的根路径 --hot 热重载,热更新.打补丁,实现浏览器的无刷新
- 收集Nginx-access,Nginx-error日志
1.配置Logstash [root@Logstash logstash]# vim /usr/local/logstash/config/nginx_log.conf input { beats ...
- POP3与SMTP以及python实现邮件的发送
什么是POP3协议: POP3是Post Office Protocol 3的简称,即邮局协议的第3个版本,它规定怎样将个人计算机连接到Internet的邮件服务器和下载电子邮件的电子协议.它是因特网 ...
- C指针与数组
通过指针遍历数组的小把戏 #include<stdio.h> #include<stdlib.h> #include<Windows.h> void main() ...
- CodeForces 840A - Leha and Function | Codeforces Round #429 (Div. 1)
/* CodeForces 840A - Leha and Function [ 贪心 ] | Codeforces Round #429 (Div. 1) A越大,B越小,越好 */ #includ ...
- 客户端xml
package lct.conference.common; import java.io.IOException;import java.io.PrintWriter;import java.net ...
- MySQL5.7.6 general tablespace
摘要: 从5.7.6开始,增加了一种新的 tablespace模式(成为general tablespace),实际上它和共享表空间比较类似:创建一个单独的ibd,ibd中包含多个表,兼容不同的格式. ...
- 把Cstring类型的字符串转化为char* 字符串;
int char_leng; Cstring str="abcd"; char_leng=str.GetLength();//获取字符串长度 char *str_temp=(cha ...
- 【线性代数】7-1:线性变换思想(The Idea of a Linear Transformation)
title: [线性代数]7-1:线性变换思想(The Idea of a Linear Transformation) categories: Mathematic Linear Algebra k ...
- win10 开启全局代理
1. 打开设置 2. 点击“网络和Internet” 3.设置手动代理 . 设置完成后就可以愉快的玩耍啦