Porównaj metody

	Samonadzorowana segmentacja semantyczna	Vision Transformer
Dziedzina	Uczenie głębokie	Uczenie głębokie
Rodzina	Machine learning	Machine learning
Rok powstania	2020–2022	2021
Twórca	Multiple groups (Caron et al.; Hamilton et al. among key contributors)	Dosovitskiy, A. et al.
Typ	Self-supervised dense prediction	Transformer architecture for images (self-attention over patches)
Źródło pierwotne	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.
Inne nazwy	SSL semantic segmentation, unsupervised semantic segmentation, label-free semantic segmentation, self-supervised dense prediction	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Pokrewne	5	5
Podsumowanie	Self-supervised semantic segmentation learns to assign a class label to every pixel of an image without relying on manually annotated segmentation masks. A backbone network is first trained on large quantities of unlabeled images using self-supervised objectives such as contrastive learning or masked image modeling, and the resulting dense features are then used to partition and label image regions, achieving competitive segmentation quality at a fraction of the annotation cost.	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).