Comparer des méthodes

	Classification d'images semi-supervisée	Apprentissage par transfert pour la classification d'images
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2013–2020	2010–2012
Auteur d'origine	Lee, D.-H. (pseudo-label); Sohn et al. (FixMatch)	Pan, S. J. & Yang, Q. (transfer learning framework); Krizhevsky, Sutskever & Hinton (deep CNN backbone)
Type	Semi-supervised deep learning	Transfer learning / supervised classification
Source fondatrice	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.	Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
Alias	SSL image classification, semi-supervised CNN classification, pseudo-label image classification, label-efficient image classification	pretrained CNN image classification, fine-tuned image classifier, domain-adapted image classifier, TL-IC
Apparentées	5	4
Résumé	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.	Transfer Learning with Image Classification reuses a deep neural network backbone — typically a CNN or Vision Transformer — pretrained on a large dataset such as ImageNet, and adapts it to classify images in a new target domain. By inheriting general visual features from the source task, the approach achieves high accuracy with far fewer labeled images than training from scratch.