Methoden vergleichen

	Segment Anything Model	Swin Transformer	Vision Transformer
Fachgebiet	Deep Learning	Deep Learning	Deep Learning
Familie	Machine learning	Machine learning	Machine learning
Entstehungsjahr	2023	2021	2021
Urheber	Alexander Kirillov	Ze Liu	Dosovitskiy, A. et al.
Typ	Neural network architecture	Neural network architecture	Transformer architecture for images (self-attention over patches)
Wegweisende Quelle	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).	Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021). Swin Transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 10012-10022).	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Aliasnamen	SAM, Segment Anything	Swin, Hierarchical Vision Transformer	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Verwandt	4	4	5
Zusammenfassung	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 Swin Transformer is a hierarchical vision transformer introduced by Liu et al. in 2021 that uses shifted window attention to achieve computational efficiency while maintaining strong performance on computer vision tasks. Unlike the original Vision Transformer which applies global self-attention, Swin uses local window-based attention with periodic shifting to balance expressiveness and efficiency.	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).