Methoden vergleichen

	Semi-supervised Vision Transformer	Vision Transformer
Fachgebiet	Deep Learning	Deep Learning
Familie	Machine learning	Machine learning
Entstehungsjahr	2021–2022	2021
Urheber	Dosovitskiy et al. (ViT); semi-supervised extensions by multiple groups (2021–2023)	Dosovitskiy, A. et al.
Typ	Semi-supervised deep learning for image understanding	Transformer architecture for images (self-attention over patches)
Wegweisende Quelle	Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. International Conference on Learning Representations (ICLR 2021).	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Aliasnamen	Semi-supervised ViT, SSL-ViT, Semi-supervised Patch-based Transformer, Semi-supervised Self-Attention Image Model	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Verwandt	6	5
Zusammenfassung	Semi-supervised Vision Transformer applies the patch-based self-attention architecture of ViT to settings where only a fraction of images are labeled, exploiting large unlabeled corpora through pseudo-labeling, consistency regularization, or self-supervised pretext tasks before fine-tuning on the small labeled set. This approach achieves near-supervised accuracy even when labeled images are scarce.	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).