Comparer des méthodes

	Réseau neuronal convolutif faiblement supervisé	CNN convolutive semi-supervisée
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2015–2016	2013–2017
Auteur d'origine	Oquab, M. et al.; Zhou, B. et al.	Lee, D.-H.; Tarvainen, A. & Valpola, H. (among others)
Type	Weakly supervised deep learning	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 Workshop on Challenges in Representation Learning.
Alias	WS-CNN, weakly supervised CNN, CNN with weak labels, CNN with noisy labels	SSL-CNN, semi-supervised CNN, self-training CNN, pseudo-label CNN
Apparentées	5	5
Résumé	A weakly supervised CNN is a convolutional neural network trained with incomplete, coarse, or noisy annotations instead of full pixel-level or bounding-box labels. Typical weak labels include image-level class tags, partial annotations, or crowd-sourced noisy labels. The model learns to classify and often to roughly localize objects using these cheaper, lower-quality supervision signals.	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.