So sánh phương pháp

	Mamba (Mô hình Không gian Trạng thái)	Transformer Thị giác
Lĩnh vực	Học sâu	Học sâu
Họ	Machine learning	Machine learning
Năm ra đời	2023	2021
Người khởi xướng	Albert Gu	Dosovitskiy, A. et al.
Loại	Neural network architecture	Transformer architecture for images (self-attention over patches)
Công trình gốc	Gu, A., & Dao, C. (2023). Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.08956.	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Tên gọi khác	Mamba, State space models, Selective state space	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Liên quan	4	5
Tóm tắt	Mamba is a sequence model architecture introduced by Gu and Dao in 2023 that achieves linear-time complexity while maintaining strong performance on language modeling tasks. By combining state space models with input-dependent selectivity, Mamba addresses the quadratic complexity of transformers while preserving modeling power.	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).