Uporedite metode

	GAN sa samonadzorom	Vision Transformer
Oblast	Duboko učenje	Duboko učenje
Porodica	Machine learning	Machine learning
Godina nastanka	2019	2021
Tvorac	Chen, T., Zhai, X., Ritter, M., Lucic, M., & Houlsby, N.	Dosovitskiy, A. et al.
Tip	Generative model with self-supervised auxiliary tasks	Transformer architecture for images (self-attention over patches)
Temeljni izvor	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.	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Drugi nazivi	SS-GAN, Self-supervised GAN, Self-supervised Generative Adversarial Network, GAN with self-supervised auxiliary tasks	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Srodne	5	5
Sažetak	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.	The Vision Transformer (ViT), introduced by Dosovitskiy and colleagues in 2021, splits an image into fixed-size patches, treats those patches as a sequence, and applies the Transformer self-attention mechanism to image classification. Given enough training data, it surpasses convolutional neural networks (CNNs).