Comparer des méthodes

	Détection d'objets semi-supervisée	Classification d'images semi-supervisée
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2020–2021	2013–2020
Auteur d'origine	Sohn et al. (STAC); Liu et al. (Unbiased Teacher)	Lee, D.-H. (pseudo-label); Sohn et al. (FixMatch)
Type	Semi-supervised learning for detection	Semi-supervised deep learning
Source fondatrice	Sohn, K., Zhang, Z., Li, C.-L., Zhang, H., Lee, C.-Y., & Pfister, T. (2020). A Simple Semi-Supervised Learning Framework for Object Detection. arXiv preprint arXiv:2005.04757.	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	SSOD, semi-supervised detection, pseudo-label object detection, label-efficient object detection	SSL image classification, semi-supervised CNN classification, pseudo-label image classification, label-efficient image classification
Apparentées	6	5
Résumé	Semi-supervised object detection trains a detector on a small labeled image set and a large unlabeled image set. A teacher model generates pseudo-labels for unlabeled images, and a student model learns from both real and pseudo-labeled data, dramatically reducing the expensive manual bounding-box annotation burden while achieving accuracy competitive with fully supervised baselines.	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.