Jämför metoder

	Online metriklärande	Siamesiskt neuralt nätverk
Ämnesområde	Maskininlärning	Djupinlärning
Familj	Machine learning	Machine learning
Ursprungsår	2004–2009	1993
Upphovsperson	Shalev-Shwartz, S.; Singer, Y.; and others	Jane Bromley & Yann LeCun et al.; popularized by Koch et al.
Typ	Online / incremental learning of distance metrics	Deep metric-learning architecture
Ursprungskälla	Shalev-Shwartz, S., Singer, Y., & Ng, A. Y. (2004). Online and batch learning of pseudo-metrics. Proceedings of the 21st International Conference on Machine Learning (ICML 2004), pp. 94. ACM.	Bromley, J., Guyon, I., LeCun, Y., Säckinger, E., & Shah, R. (1993). Signature verification using a 'Siamese' time delay neural network. Advances in Neural Information Processing Systems, 6.
Alias	OML, incremental metric learning, streaming metric learning, online distance metric learning	twin network, Siamese neural network, contrastive metric network, Siyam ağı
Närliggande	3	1
Sammanfattning	Online Metric Learning adapts a Mahalanobis distance metric incrementally as new labeled examples or pairwise constraints arrive one at a time, without storing the full dataset. It merges the efficiency of online learning with the representational power of metric learning, making it suitable for streaming, large-scale, or continually changing environments where retraining from scratch is impractical.	A Siamese network is a deep architecture with two (or more) identical, weight-sharing branches that map inputs into an embedding space where similar inputs land close together and dissimilar ones far apart. Introduced by Bromley, LeCun, and colleagues in 1993 for signature verification and revived by Koch et al. (2015) for one-shot image recognition, it learns a similarity metric rather than fixed class labels, making it ideal for verification, matching, and few-shot tasks.