Sammenlign metoder

	Swin Transformer	DETR (Detection Transformer)	Vision Transformer
Fagområde	Dyb læring	Dyb læring	Dyb læring
Familie	Machine learning	Machine learning	Machine learning
Oprindelsesår	2021	2020	2021
Ophavsperson	Ze Liu	Nicolas Carion	Dosovitskiy, A. et al.
Type	Neural network architecture	Neural network architecture	Transformer architecture for images (self-attention over patches)
Oprindelig kilde	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).	Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020). End-to-end object detection with transformers. In European Conference on Computer Vision (pp. 213-229). Springer, Cham.	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Aliasser	Swin, Hierarchical Vision Transformer	Detection Transformer, DETR	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Relaterede	4	4	5
Resumé	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.	DETR (Detection Transformer) is an end-to-end framework for object detection introduced by Carion et al. in 2020 that reformulates detection as a direct set prediction problem using transformers. Unlike traditional approaches that use hand-crafted post-processing like non-maximum suppression, DETR treats object detection as a sequence-to-sequence problem where the transformer predicts all objects at once.	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).