Compară metode

	Modelul Segment Anything	Vision Transformer
Domeniu	Învățare profundă	Învățare profundă
Familie	Machine learning	Machine learning
Anul apariției	2023	2021
Autorul original	Alexander Kirillov	Dosovitskiy, A. et al.
Tip	Neural network architecture	Transformer architecture for images (self-attention over patches)
Sursa seminală	Kirillov, A., Mintun, E., Darrell, T., & Girshick, R. (2023). Segment Anything. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 4015-4026).	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Denumiri alternative	SAM, Segment Anything	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Înrudite	4	5
Rezumat	Segment Anything Model (SAM) is a foundation model introduced by Kirillov et al. in 2023 that can segment any object in an image given various forms of prompts. SAM is trained on a massive dataset of diverse images and learns to segment objects based on minimal user input such as points, boxes, or text descriptions.	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).