Deep Learning based Large Scale Visual Recommendation and Search for E-Commerce
来源：互联网 发布：厦门大学网络教育本科 编辑：程序博客网 时间：2024/06/06 01:36
一篇用于相似物品的图片推荐的paper，github地址
网络结构如下所示
图a展示的是整体的框架，每个VisNet具体细节如图b所示。
VisNet是具有两个分支：一个传统 的VGG16和一个浅层网络（kernel size 较大）
VGG16用于提取 high level/ abstract details
浅层网络用于提取 low level/fine-graind details
triplet loss也用于此。
（q,p,n）
a query image (q), a positive image (p) and a negative image (n)
The in-class triplets 让网络学会细微的差异，The out-of-class triplets让网络学会coarse-grained 差别。
测试的时候，是对每张图片直接提取图b中最后输出的feature vector，之后再用距离度量方式度量差异性。
0 0
- Deep Learning based Large Scale Visual Recommendation and Search for E-Commerce
- cvpr-Edgel Index for Large-Scale Sketch-based Image Search
- The Intersection of Large-Scale Graph Analytics and Deep Learning
- Analysis of recommendation algorithms for e-commerce
- Discriminative Learning of Relaxed Hierarchy for Large-scale Visual Recognition
- Supervised Learning of Semantics-Preserving Hashing via Deep Neural Networks for Large-Scale Image S
- 《E-Commerce Recommendation Applications》笔记
- [论文学习]Deep Learning Based Recommendation: A Survey
- [Paper Reading]--Joint multi-model representations for e-commerce catalog search driven by visual
- 论文导读（large－scale image retrieval）——large-scale E-commerce Image retrieval with Top-weighted CNN
- Jointly Learning Binary Code for Large-scale Face Image Retrieval and Attributes Prediction
- Hamming embedding and weak geometric consistency for large scale image search
- 论文阅读《Hamming embedding and weak geometric consistency for large scale image search》
- Deep content-based music recommendation
- 论文笔记：Personalized Deep Learning for Tag Recommendation
- Large Scale Machine Learning
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Deep Fisher Networks for Large-Scale Image Classification（精读）
- 英语月总结
- 单例模式
- Windows 调用Dll
- [数据结构]冒泡排序
- spring3注解方式无法注入servlet和filter
- Deep Learning based Large Scale Visual Recommendation and Search for E-Commerce
- linux的命令解析器和常用的快捷键（以及简单的目录结构）
- 正式工作一年的一些小感想
- eclipse 卸载svn 插件 安装svn
- 4.1 11091 最优自然数分解问题
- .NET 环境中使用RabbitMQ
- 2017.4.29接口
- A^X mod P 大幂分解求和 打表
- Android 设置横屏竖屏
