# Siamese Neural Network > Source: > Published: 2026-08-13 17:29:53+00:00 # Siamese neural network A **Siamese neural network** (sometimes called a **twin neural network**) is an [artificial neural network](https://en.wikipedia.org/wiki/Artificial_neural_network) that uses the same weights while working in tandem on two different input vectors to compute comparable output vectors.[[1]](#cite_note-1)[[2]](#cite_note-2) [3] Often one of the output vectors is precomputed, thus forming a baseline against which the other output vector is compared. This is similar to comparing [fingerprints](https://en.wikipedia.org/wiki/Fingerprint)but can be described more technically as a distance function for [locality-sensitive hashing](https://en.wikipedia.org/wiki/Locality-sensitive_hashing). [ *]*[citation needed](https://en.wikipedia.org/wiki/Wikipedia:Citation_needed)It is possible to build an architecture that is functionally similar to a twin network but implements a slightly different function. This is typically used for comparing similar instances in different type sets.[ [citation needed](https://en.wikipedia.org/wiki/Wikipedia:Citation_needed)] Uses of similarity measures where a twin network might be used are such things as [recognizing handwritten](https://en.wikipedia.org/wiki/Handwriting_recognition) checks, automatic [detection of faces](https://en.wikipedia.org/wiki/Face_detection) in camera images, and matching text queries with indexed documents [4]. The perhaps most well-known application of twin networks are [face recognition](https://en.wikipedia.org/wiki/Face_recognition), where known images of people are precomputed and compared to an image from a turnstile or similar. 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, that is the facial recognition problem. [DeepFace](https://en.wikipedia.org/wiki/DeepFace)is an example of such a system. In its most extreme form this is recognizing a single person at a train station or airport. The other is [[3]](#cite_note-:0-3)[face verification](https://en.wikipedia.org/wiki/Face_verification), that is for example, to verify whether a photo in a passport matches the face of the passport's owner. The twin network might be the same, but the implementation can be quite different. ## Learning [[edit](/w/index.php?title=Siamese_neural_network&action=edit§ion=1)] Learning in twin networks can be done with [triplet loss](https://en.wikipedia.org/wiki/Triplet_loss) or [contrastive loss](https://en.wikipedia.org/wiki/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. A distance metric for a loss function may have the following properties[[5]](#cite_note-5) - Non-negativity: - Identity of Non-discernibles: - Commutativity: [Triangle inequality](https://en.wikipedia.org/wiki/Triangle_inequality): In particular, the triplet loss algorithm is often defined with squared Euclidean (which unlike Euclidean, does not have triangle inequality) distance at its core. ### Predefined metrics, Euclidean distance metric [[edit](/w/index.php?title=Siamese_neural_network&action=edit§ion=2)] The common learning goal is to minimize a distance metric for similar objects and maximize for distinct ones. This gives a loss function like - are indexes into a set of vectors - function implemented by the twin network The most common distance metric used is [Euclidean distance](https://en.wikipedia.org/wiki/Euclidean_distance), in case of which the loss function can be rewritten in matrix form as ### Learned metrics, nonlinear distance metric [[edit](/w/index.php?title=Siamese_neural_network&action=edit§ion=3)] A more general case is where the output vector from the twin network is passed through additional network layers implementing non-linear distance metrics. - are indexes into a set of vectors - function implemented by the twin network - function implemented by the network joining outputs from the twin network On a matrix form the previous is often approximated as a [Mahalanobis distance](https://en.wikipedia.org/wiki/Mahalanobis_distance) for a linear space as[[6]](#cite_note-6) This can be further subdivided in at least [Unsupervised learning](https://en.wikipedia.org/wiki/Unsupervised_learning) and [Supervised learning](https://en.wikipedia.org/wiki/Supervised_learning). ### Learned metrics, half-twin networks [[edit](/w/index.php?title=Siamese_neural_network&action=edit§ion=4)] This form also allows the twin network to be more of a half-twin, implementing a slightly different functions - are indexes into a set of vectors - function implemented by the half-twin network - function implemented by the network joining outputs from the twin network ## Twin networks for object tracking [[edit](/w/index.php?title=Siamese_neural_network&action=edit§ion=5)] Twin networks have been used in object tracking because of its unique two tandem inputs and similarity measurement. In object tracking, one input of the twin network is user pre-selected exemplar image, the other input is a larger search image. The twin network's job is to locate the exemplar inside of the search image. By measuring the similarity between exemplar and each part of the search image, a map of similarity score can be given by the twin network. Furthermore, using a Fully Convolutional Network, the process of computing each sector's similarity score can be replaced with only one cross correlation layer.[[7]](#cite_note-7) After being first introduced in 2016, Twin fully convolutional network has been used in many High-performance Real-time Object Tracking Neural Networks. Like CFnet, [8] StructSiam, SiamFC-tri, [[9]](#cite_note-9)DSiam, [[10]](#cite_note-10)SA-Siam, [[11]](#cite_note-11)SiamRPN, [[12]](#cite_note-12)DaSiamRPN, [[13]](#cite_note-13)Cascaded SiamRPN, [[14]](#cite_note-14)SiamMask, [[15]](#cite_note-15)SiamRPN++, [[16]](#cite_note-16)Deeper and Wider SiamRPN. [[17]](#cite_note-17) [[18]](#cite_note-18)## See also [[edit](/w/index.php?title=Siamese_neural_network&action=edit§ion=6)] ## References [[edit](/w/index.php?title=Siamese_neural_network&action=edit§ion=7)] [↑](#cite_ref-1)Bromley, Jane; Guyon, Isabelle; LeCun, Yann; Säckinger, Eduard; Shah, Roopak (1994).["Signature verification using a "Siamese" time delay neural network"](https://papers.neurips.cc/paper_files/paper/1993/file/288cc0ff022877bd3df94bc9360b9c5d-Paper.pdf)(PDF).*Advances in Neural Information Processing Systems*.**6**: 737–744.[↑](#cite_ref-2)Chopra, S.; Hadsell, R.; LeCun, Y. (June 2005). "Learning a Similarity Metric Discriminatively, with Application to Face Verification".*2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)*. Vol. 1. pp. 539–546 vol. 1.[doi](https://en.wikipedia.org/wiki/Doi_(identifier)):[10.1109/CVPR.2005.202](https://doi.org/10.1109%2FCVPR.2005.202).[ISBN](https://en.wikipedia.org/wiki/ISBN_(identifier))[0-7695-2372-2](https://en.wikipedia.org/wiki/Special:BookSources/0-7695-2372-2).[S2CID](https://en.wikipedia.org/wiki/S2CID_(identifier))[5555257](https://api.semanticscholar.org/CorpusID:5555257).[1](#cite_ref-:0_3-0)[2](#cite_ref-:0_3-1)Taigman, Y.; Yang, M.; Ranzato, M.; Wolf, L. (June 2014). "DeepFace: Closing the Gap to Human-Level Performance in Face Verification".*2014 IEEE Conference on Computer Vision and Pattern Recognition*. pp. 1701–1708.[doi](https://en.wikipedia.org/wiki/Doi_(identifier)):[10.1109/CVPR.2014.220](https://doi.org/10.1109%2FCVPR.2014.220).[ISBN](https://en.wikipedia.org/wiki/ISBN_(identifier))[978-1-4799-5118-5](https://en.wikipedia.org/wiki/Special:BookSources/978-1-4799-5118-5).[S2CID](https://en.wikipedia.org/wiki/S2CID_(identifier))[2814088](https://api.semanticscholar.org/CorpusID:2814088).[↑](#cite_ref-4)["Siamese Recurrent Architectures for Learning Sentence Similarity"](https://ojs.aaai.org/index.php/AAAI/article/view/10350).[↑](#cite_ref-5)Chatterjee, Moitreya; Luo, Yunan.["Similarity Learning with (or without) Convolutional Neural Network"](http://slazebni.cs.illinois.edu/spring17/lec09_similarity.pdf)(PDF). Retrieved 2018-12-07.[↑](#cite_ref-6)Chandra, M.P. (1936).["On the generalized distance in statistics"](http://library.isical.ac.in:8080/jspui/bitstream/123456789/6765/1/Vol02_1936_1_Art05-pcm.pdf)(PDF).*Proceedings of the National Institute of Sciences of India*. 1.**2**: 49–55.[↑](#cite_ref-7)Fully-Convolutional Siamese Networks for Object Tracking[arXiv](https://en.wikipedia.org/wiki/ArXiv_(identifier)):[1606.09549](https://arxiv.org/abs/1606.09549)[↑](#cite_ref-8)["End-to-end representation learning for Correlation Filter based tracking"](https://www.robots.ox.ac.uk/~luca/cfnet.html).[↑](#cite_ref-9)["Structured Siamese Network for Real-Time Visual Tracking"](http://openaccess.thecvf.com/content_ECCV_2018/papers/Yunhua_Zhang_Structured_Siamese_Network_ECCV_2018_paper.pdf)(PDF).[↑](#cite_ref-10)["Triplet Loss in Siamese Network for Object Tracking"](http://openaccess.thecvf.com/content_ECCV_2018/papers/Xingping_Dong_Triplet_Loss_with_ECCV_2018_paper.pdf)(PDF).[↑](#cite_ref-11)["Learning Dynamic Siamese Network for Visual Object Tracking"](http://openaccess.thecvf.com/content_ICCV_2017/papers/Guo_Learning_Dynamic_Siamese_ICCV_2017_paper.pdf)(PDF).[↑](#cite_ref-12)["A Twofold Siamese Network for Real-Time Object Tracking"](http://openaccess.thecvf.com/content_cvpr_2018/papers/He_A_Twofold_Siamese_CVPR_2018_paper.pdf)(PDF).[↑](#cite_ref-13)["High Performance Visual Tracking with Siamese Region Proposal Network"](http://openaccess.thecvf.com/content_cvpr_2018/papers/Li_High_Performance_Visual_CVPR_2018_paper.pdf)(PDF).[↑](#cite_ref-14)Zhu, Zheng; Wang, Qiang; Li, Bo; Wu, Wei; Yan, Junjie; Hu, Weiming (2018). "Distractor-aware Siamese Networks for Visual Object Tracking".[arXiv](https://en.wikipedia.org/wiki/ArXiv_(identifier)):[1808.06048](https://arxiv.org/abs/1808.06048)[[cs.CV](https://arxiv.org/archive/cs.CV)].[↑](#cite_ref-15)Fan, Heng; Ling, Haibin (2018). "Siamese Cascaded Region Proposal Networks for Real-Time Visual Tracking".[arXiv](https://en.wikipedia.org/wiki/ArXiv_(identifier)):[1812.06148](https://arxiv.org/abs/1812.06148)[[cs.CV](https://arxiv.org/archive/cs.CV)].[↑](#cite_ref-16)Wang, Qiang; Zhang, Li; Bertinetto, Luca; Hu, Weiming; Torr, Philip H. S. (2018). "Fast Online Object Tracking and Segmentation: A Unifying Approach".[arXiv](https://en.wikipedia.org/wiki/ArXiv_(identifier)):[1812.05050](https://arxiv.org/abs/1812.05050)[[cs.CV](https://arxiv.org/archive/cs.CV)].[↑](#cite_ref-17)Li, Bo; Wu, Wei; Wang, Qiang; Zhang, Fangyi; Xing, Junliang; Yan, Junjie (2018). "SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks".[arXiv](https://en.wikipedia.org/wiki/ArXiv_(identifier)):[1812.11703](https://arxiv.org/abs/1812.11703)[[cs.CV](https://arxiv.org/archive/cs.CV)].[↑](#cite_ref-18)Zhang, Zhipeng; Peng, Houwen (2019). "Deeper and Wider Siamese Networks for Real-Time Visual Tracking".[arXiv](https://en.wikipedia.org/wiki/ArXiv_(identifier)):[1901.01660](https://arxiv.org/abs/1901.01660)[[cs.CV](https://arxiv.org/archive/cs.CV)].