手法を比較

	自己教師あり距離学習	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	2020 (modern contrastive formulation); foundations 1990s–2000s	2003 (foundational); refined 2009 (LMNN)	1993
提唱者	Chen, T. et al. (SimCLR); earlier metric learning foundations by Bromley, LeCun (1994)	Xing, E. P.; Jordan, M. I.; Russell, S.; Ng, A. Y.	Jane Bromley & Yann LeCun et al.; popularized by Koch et al.
種類	Self-supervised representation learning with metric objective	Representation learning / supervised distance optimization	Deep metric-learning architecture
原典	Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A Simple Framework for Contrastive Learning of Visual Representations. Proceedings of the 37th International Conference on Machine Learning (ICML 2020), PMLR 119, 1597–1607.	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	self-supervised representation learning with metric loss, contrastive self-supervised learning, unsupervised metric learning, SSML	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	Self-supervised metric learning trains a neural encoder to embed inputs so that semantically similar items lie close together in vector space, using automatically generated pseudo-labels instead of human annotations. By combining self-supervised pretext tasks with contrastive or triplet-based metric objectives, it produces transferable, label-efficient representations applicable to retrieval, clustering, and few-shot classification.	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.