Σύγκριση μεθόδων

	Μετασχηματιστής Όρασης Αυτο-εποπτευόμενος	Vision Transformer
Πεδίο	Βαθιά Μάθηση	Βαθιά Μάθηση
Οικογένεια	Machine learning	Machine learning
Έτος προέλευσης	2021–2022	2021
Δημιουργός	Caron et al. (DINO); He et al. (MAE)	Dosovitskiy, A. et al.
Τύπος	Self-supervised pre-training for vision transformers	Transformer architecture for images (self-attention over patches)
Θεμελιώδης πηγή	Caron, M., Touvron, H., Misra, I., Jegou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021). Emerging Properties in Self-Supervised Vision Transformers. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 9650–9660.	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Εναλλακτικές ονομασίες	SSL-ViT, self-supervised ViT, unsupervised ViT pre-training, vision transformer self-supervised pre-training	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Συναφείς	4	5
Σύνοψη	Self-supervised Vision Transformer (SSL-ViT) applies self-supervised pre-training objectives — such as masked patch prediction (MAE) or self-distillation with no labels (DINO) — to the Vision Transformer architecture, enabling powerful visual representations to be learned from large unlabeled image corpora before any task-specific fine-tuning.	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).