1707.Deep Learning for Person Reidentification Using Support Vector Machines 论文笔记

作者文章参考自:

S.-Z. Chen, C.-C. Guo, and J.-H. Lai, “Deep ranking for person re-identifcation via joint representation learning,” IEEETransactions on Image Processing, vol. 25, no. 5, pp. 2353–2367,2016.其顶层采用的是ranking layer,作者采用了其样本对作为一张图片输入的网络架构
Y. Tang, Deep Learning Using Support Vector Machines, CoRR,2013 参考了向量机部分,引入了可微的L2-SVM,并用一个分支代替了两个分支输入。

网络架构如下:
1707.Deep Learning for Person Reidentification Using Support Vector Machines 论文笔记
1707.Deep Learning for Person Reidentification Using Support Vector Machines 论文笔记

实验在CUHK01和VIPeR上进行,实验效果一般!

训练用的一些技巧:DropOut,BN,Data Augmentation 和初期训练的样本对 Data Balancing,预训练在CUHK02上,在CUHK01和VIPeR上测试时会finetune 预训练模型的最后几层。
1707.Deep Learning for Person Reidentification Using Support Vector Machines 论文笔记

其他实验验证:
Superiority of Joint Representation Learning
1707.Deep Learning for Person Reidentification Using Support Vector Machines 论文笔记

Superiority of Linear SVM Layer
1707.Deep Learning for Person Reidentification Using Support Vector Machines 论文笔记

总结:
文中关于网络层公式的推导和梯度反传推导值得参考。