[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
- Python跨文件全局变量的使用
尽管某些书籍上总是说避免使用全局变量,但是在实际的需求不断变化中,往往定义一个全局变量是最可靠的方法,但是又必须要避免变量名覆盖. Python 中 global 关键字可以定义一个变量为全局变量,但 ...
- 阿里云申请免费SSL证书,并配置到Tomcat,实现https访问
第一步:阿里云免费https证书安装 https://jingyan.baidu.com/article/fdffd1f8619481f3e98ca196.html 第二步:阿里云申请免费SSL证书 ...
- BZOJ 3218 A + B Problem (可持久化线段树+最小割)
做法见dalao博客 geng4512的博客, 思路就是用线段树上的结点来进行区间连边.因为有一个只能往前面连的限制,所以还要可持久化.(duliu) 一直以来我都是写dinicdinicdinic做 ...
- 5、Spring Boot 2.x 启动原理解析
1.5 Spring Boot 启动原理解析 前言 前面几章我们见识了SpringBoot为我们做的自动配置,确实方便快捷,但是对于新手来说,如果不大懂SpringBoot内部启动原理,以后难免会吃亏 ...
- .Net Core:Middleware自定义中间件
新建standard类库项目,添加引用包 Microsoft.AspNetCore 1.扩展IApplicationBuilder using Microsoft.AspNetCore.Builder ...
- String.getBytes()方法中的中文编码问题(转)
String的getBytes()方法是得到一个系统默认的编码格式的字节数组getBytes("utf-8") 得到一个UTF-8格式的字节数组 把String转换成bytes, ...
- Oracle 11g关闭用户连接审计
sys.aud$表数据量增长较快.这时,不想关闭数据库的审计,但是又不想频繁的清理sys.aud$表.可进行如下操作关闭数据库连接的审计 noaudit connect;
- 参数类型 (@Test层)常用参数
long lNum = 1234L; float fNum = 1.23f; double dNum = 1.23d;
- 2018-2019 ACM-ICPC, China Multi-Provincial Collegiate Programming Contest
目录 Contest Info Solutions A. Maximum Element In A Stack B. Rolling The Polygon C. Caesar Cipherq D. ...
- 【线性代数】5-3:克莱姆法则,逆和体积(Cramer's Rule,Inverses,and Volumes)
title: [线性代数]5-3:克莱姆法则,逆和体积(Cramer's Rule,Inverses,and Volumes) categories: Mathematic Linear Algebr ...