旷视的AlignedReID,很有意思。
The end-to-end learning with structure prior is more powerful than a “blind” end-to-end learning.
reid难点:
目前triplet loss等用的比较多。Combining softmax loss with metric learning loss to speed up the convergence is also a popular method. 还有一些考虑局部特征如pose和part的方法,具体见论文。
AlignedReID
注意local feature就是先做一个方向的global pooling(垂直纸面方向),然后用1*1卷积降低通道数到128,这样就把图片中水平的信息在图片的宽度方向上进行了叠加。global feature用L2计算距离,local