השוואת שיטות

	למידת מטריקה בפיקוח עצמי	למידה בפיקוח עצמי	רשת סיאמית
תחום	למידת מכונה	למידת מכונה	למידה עמוקה
משפחה	Machine learning	Machine learning	Machine learning
שנת המקור	2020 (modern contrastive formulation); foundations 1990s–2000s	2018–2020	1993
הוגה השיטה	Chen, T. et al. (SimCLR); earlier metric learning foundations by Bromley, LeCun (1994)	LeCun, Y. and community (formalized ~2018–2020)	Jane Bromley & Yann LeCun et al.; popularized by Koch et al.
סוג	Self-supervised representation learning with metric objective	Representation learning paradigm	Deep metric-learning architecture
מקור מכונן	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.	LeCun, Y. & Misra, I. (2022). Self-supervised learning: The dark matter of intelligence. Meta AI Blog. https://ai.facebook.com/blog/self-supervised-learning-the-dark-matter-of-intelligence/	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.
כינויים	self-supervised representation learning with metric loss, contrastive self-supervised learning, unsupervised metric learning, SSML	SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning	twin network, Siamese neural network, contrastive metric network, Siyam ağı
קשורות	3	3	1
תקציר	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.	Self-supervised learning (SSL) is a machine-learning paradigm that generates its own supervisory signal directly from unlabeled data by defining an auxiliary pretext task — such as predicting masked words, rotating images, or contrasting augmented views — and uses the learned representations as a powerful starting point for downstream tasks with minimal labeled examples.	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.