Comparer des méthodes

	Classification d'images faiblement supervisée	Classification d'images semi-supervisée
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2014–2016	2013–2020
Auteur d'origine	Multiple contributors; class activation map approach: Zhou et al.	Lee, D.-H. (pseudo-label); Sohn et al. (FixMatch)
Type	Weakly supervised deep learning paradigm	Semi-supervised deep learning
Source fondatrice	Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016). Learning Deep Features for Discriminative Localization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2921–2929.	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	WSL image classification, image-level supervised classification, noisy-label image classification, weakly labeled visual recognition	SSL image classification, semi-supervised CNN classification, pseudo-label image classification, label-efficient image classification
Apparentées	5	5
Résumé	Weakly supervised image classification trains convolutional or transformer-based networks using only coarse, incomplete, or noisy supervision — such as image-level category labels, hashtags, or web-scraped tags — without requiring precise bounding boxes or pixel annotations. This dramatically reduces labeling cost while still enabling high-accuracy visual recognition at scale.	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.