Comparer des méthodes

	Régression logistique auto-supervisée	Régression logistique (ML)
Domaine	Apprentissage automatique	Apprentissage automatique
Famille	Machine learning	Machine learning
Année d'origine	2020s	1958
Auteur d'origine	Chen et al. (SimCLR linear evaluation protocol, 2020); logistic probe practice widely adopted across SSL literature	Cox, D. R.
Type	Self-supervised pretraining + supervised linear classification	Probabilistic linear classifier
Source fondatrice	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), 1597–1607.	Cox, D. R. (1958). The regression analysis of binary sequences. Journal of the Royal Statistical Society, Series B, 20(2), 215–242.
Alias	SSL linear probe, contrastive pretraining with logistic classifier, self-supervised linear evaluation, SSL + logistic regression	logit model, logit regression, binomial logistic regression, maximum entropy classifier
Apparentées	5	5
Résumé	Self-supervised logistic regression is a two-stage pipeline in which a neural encoder is first trained on abundant unlabeled data through a self-supervised pretext task — such as contrastive learning or masked prediction — and then the frozen learned representations are classified with a standard logistic regression model trained on a small labeled dataset. This linear evaluation protocol is widely used to benchmark the quality of self-supervised representations.	Logistic regression is a foundational probabilistic classifier that models the log-odds of a binary (or multinomial) outcome as a linear function of the predictors. Introduced by D. R. Cox in 1958, it remains one of the most widely used and interpretable classification methods in both statistics and machine learning, valued for its calibrated probability outputs and clear coefficient interpretation.