【Move to another page】
Quote
https://ift.tt/2G5YpqS
Siamese network
Jeblad: removed Category:Neural networks; added Category:Artificial neural networks using HotCat
'''Siamese network''' is an [[artificial neural network]] that use the same weights while working in tandem on two different input vectors to compute comparable output vectors. Often one of the output vectors are precomputed, thus forming a baseline the other output vector are compared against. This is similar to a comparing [[Fingerprint|fingerprints]] or more technical as a distance function for [[Locality-sensitive hashing]].
The perhaps mos well-known application of siamese networks are face recognition, where known images of people are precomputed and compared to an image from a turnstile or similar.<ref>Liquid error: wrong number of arguments (1 for 2)</ref> It is not obvious at first, but there are two slightly different problems. One is recognizing a person among a large number of other persons. In its most extreme form this is recognizing a single person at a train station or airport. The other is to verify whether the photo in a pass is the same as the person claiming he or she is the same person. The siamese network might be the same, but the implementation can be quite different.
Learning in siamese networks can be done with [[triplet loss]] or [[contrastive loss]]. For learning by triplet loss a baseline vector (anchor image) is compared against a positive vector (truthy image) and a negative vector (falsy image). The negative vector will force learning in the network, while the positive vector will act like a regularizer. For learning by contrastive loss there must be a weight decay to regularize the weights, or some similar operation like a normalization.
== References ==
<references />
[[Category:Artificial neural networks]]
The perhaps mos well-known application of siamese networks are face recognition, where known images of people are precomputed and compared to an image from a turnstile or similar.<ref>Liquid error: wrong number of arguments (1 for 2)</ref> It is not obvious at first, but there are two slightly different problems. One is recognizing a person among a large number of other persons. In its most extreme form this is recognizing a single person at a train station or airport. The other is to verify whether the photo in a pass is the same as the person claiming he or she is the same person. The siamese network might be the same, but the implementation can be quite different.
Learning in siamese networks can be done with [[triplet loss]] or [[contrastive loss]]. For learning by triplet loss a baseline vector (anchor image) is compared against a positive vector (truthy image) and a negative vector (falsy image). The negative vector will force learning in the network, while the positive vector will act like a regularizer. For learning by contrastive loss there must be a weight decay to regularize the weights, or some similar operation like a normalization.
== References ==
<references />
[[Category:Artificial neural networks]]
December 08, 2018 at 12:11AM
