Porównaj metody

	Samouczenie segmentacji instancji	Vision Transformer
Dziedzina	Uczenie głębokie	Uczenie głębokie
Rodzina	Machine learning	Machine learning
Rok powstania	2021–2022	2021
Twórca	Wang et al. (FreeSOLO); Caron et al. (DINO)	Dosovitskiy, A. et al.
Typ	Self-supervised deep learning for pixel-level object delineation	Transformer architecture for images (self-attention over patches)
Źródło pierwotne	Wang, X., Zhu, Z., Cao, G., Yao, Z., Jiang, Z., & Ye, J. (2022). FreeSOLO: Learning to Segment Objects without Annotations. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 14176–14186.	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Inne nazwy	SSIS, unsupervised instance segmentation, label-free instance segmentation, self-supervised mask prediction	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Pokrewne	4	5
Podsumowanie	Self-supervised instance segmentation learns to detect and delineate individual object instances in images without any human-annotated masks or bounding boxes. Instead of relying on costly pixel-level labels, it exploits self-supervised pretraining, multi-view consistency, and pseudo-label generation to discover and segment objects purely from raw image data.	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).