Comparer des méthodes

	CNN convolutive semi-supervisée	Classification d'images semi-supervisée
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2013–2017	2013–2020
Auteur d'origine	Lee, D.-H.; Tarvainen, A. & Valpola, H. (among others)	Lee, D.-H. (pseudo-label); Sohn et al. (FixMatch)
Type	Semi-supervised deep learning	Semi-supervised deep learning
Source fondatrice	Lee, D.-H. (2013). Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. ICML Workshop on Challenges in Representation Learning.	Lee, D.-H. (2013). Pseudo-Label: The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks. ICML 2013 Workshop on Challenges in Representation Learning.
Alias	SSL-CNN, semi-supervised CNN, self-training CNN, pseudo-label CNN	SSL image classification, semi-supervised CNN classification, pseudo-label image classification, label-efficient image classification
Apparentées	5	5
Résumé	A Semi-supervised CNN trains a convolutional network on a small labeled image set and a larger pool of unlabeled images simultaneously, using techniques such as pseudo-labeling and consistency regularization to extract supervisory signal from unlabeled data. This strategy closes much of the performance gap caused by scarce annotations without requiring additional human labeling effort.	Semi-supervised image classification trains deep neural networks on a small set of labeled images together with a much larger pool of unlabeled images. Techniques such as pseudo-labeling, consistency regularization, and confidence thresholding allow the model to leverage the structure of unlabeled data, dramatically reducing the need for expensive manual annotation while approaching fully-supervised accuracy.