Comparer des méthodes

	Swin Transformer	Mamba Vision	Vision Transformer
Domaine	Apprentissage profond	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning	Machine learning
Année d'origine	2021	2024	2021
Auteur d'origine	Ze Liu	Li Zhu	Dosovitskiy, A. et al.
Type	Neural network architecture	Neural network architecture	Transformer architecture for images (self-attention over patches)
Source fondatrice	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).	Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., & Wang, X. (2024). Vision Mamba: Efficient state space models for image understanding. In International Conference on Machine Learning.	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Alias	Swin, Hierarchical Vision Transformer	ViM, Mamba for Vision	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Apparentées	4	4	5
Résumé	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.	Vision Mamba is an efficient state space model approach for image understanding introduced in 2024 that adapts Mamba, a linear-complexity sequence model, to computer vision. By reformulating image tokens as sequences and using state space models, Vision Mamba achieves competitive accuracy with transformers while maintaining linear computational complexity.	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).