緣起於尋找caffe如何輸入多通道圖片（兩張四通道圖片），希望通過尋找制作lmdb時，遇到的datum，來得到如何設置lmdb的通道。結果發現了siamese網絡。
摘抄自caffe github的issue697
Siamese nets are supervised models for metric learning [1].
[1] S. Chopra, R. Hadsell, and Y. LeCun. Learning a similarity metric discriminatively, with application to face verification. In Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, volume 1, pages 539–546. IEEE, 2005. http://yann.lecun.com/exdb/publis/pdf/chopra-05.pdf
Speaking of metric learning, I remember that @norouzi had proposed and open sourced a method that learned a Hamming distance metric to distinguish similar and dissimilar images [2].
[2] Mohammad Norouzi, David J. Fleet, Ruslan Salakhutdinov, Hamming Distance Metric Learning, Neural Information Processing Systems (NIPS), 2012.
以及一些論文需要看看：
2015CVPR：
[1]MatchNet:Unifying Feature and Metric Learning for Patch-Based Matching
[2]Learning to Compare Image Patches via Convolutional Neural Network
[3]Image Patch Matching Using Convolutional Descriptors with Euclidean Distance
大體上說，這些論文的思路都是利用一對CNN來提取一對圖像特征，然后通過歐氏距離（經典如Siamese網絡）或通過全連接網絡（MatchNet）來實現特征的對比，最后通過交叉熵函數來完成優化。