手法を比較

	オンライン距離学習	距離学習	シャムニューラルネットワーク
分野	機械学習	機械学習	深層学習
系統	Machine learning	Machine learning	Machine learning
提唱年	2004–2009	2003 (foundational); refined 2009 (LMNN)	1993
提唱者	Shalev-Shwartz, S.; Singer, Y.; and others	Xing, E. P.; Jordan, M. I.; Russell, S.; Ng, A. Y.	Jane Bromley & Yann LeCun et al.; popularized by Koch et al.
種類	Online / incremental learning of distance metrics	Representation learning / supervised distance optimization	Deep metric-learning architecture
原典	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.	Xing, E. P., Jordan, M. I., Russell, S., & Ng, A. Y. (2003). Distance metric learning with application to clustering with side-information. In Advances in Neural Information Processing Systems (NIPS), 16, 505–512.	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.
別名	OML, incremental metric learning, streaming metric learning, online distance metric learning	Distance Metric Learning, Similarity Learning, DML, Representation Learning via Distance	twin network, Siamese neural network, contrastive metric network, Siyam ağı
関連	3	5	1
概要	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.	Metric learning is a machine-learning framework that trains a distance or similarity function from data so that semantically similar examples end up close together in the learned space while dissimilar examples are pushed apart. Unlike fixed distances such as Euclidean, the learned metric adapts to the structure of the task, making downstream classifiers, clusterers, and retrieval systems significantly more accurate.	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.