Сравнение на методи

	GAN с надзор чрез самообучение	Самообучаваща се конволюционна невронна мрежа
Област	Дълбоко обучение	Дълбоко обучение
Семейство	Machine learning	Machine learning
Година на възникване	2019	2018–2020
Създател	Chen, T., Zhai, X., Ritter, M., Lucic, M., & Houlsby, N.	LeCun, Y. (CNN backbone); Chen et al. and He et al. (self-supervised visual frameworks)
Тип	Generative model with self-supervised auxiliary tasks	Self-supervised deep learning
Основополагащ източник	Chen, T., Zhai, X., Ritter, M., Lucic, M., & Houlsby, N. (2019). Self-Supervised GANs via Auxiliary Rotation Loss. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 12154–12163.	Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A Simple Framework for Contrastive Learning of Visual Representations. In Proceedings of the 37th International Conference on Machine Learning (ICML 2020), PMLR 119, 1597–1607.
Други названия	SS-GAN, Self-supervised GAN, Self-supervised Generative Adversarial Network, GAN with self-supervised auxiliary tasks	Self-supervised CNN, SSL-CNN, contrastive CNN, pretext-task CNN
Свързани	5	5
Резюме	Self-supervised GAN augments a standard Generative Adversarial Network with one or more self-supervised auxiliary tasks — such as predicting image rotation or patch position — that stabilise adversarial training and yield a discriminator that learns rich, transferable representations from unlabeled data without requiring manual annotations.	A self-supervised convolutional neural network (CNN) learns powerful visual representations from unlabeled images by solving pretext tasks — such as contrastive instance discrimination or masked-patch prediction — and then fine-tunes on a small labeled set. This approach dramatically reduces dependence on large annotated datasets while preserving the spatial feature-extraction strengths of convolutional architectures.