手法を比較

	Vision Mamba	Mamba（ステート空間モデル）	空間時間グラフ畳み込みネットワーク	ビジョントランスフォーマー
分野	深層学習	深層学習	深層学習	深層学習
系統	Machine learning	Machine learning	Machine learning	Machine learning
提唱年	2024	2023	2018	2021
提唱者	Li Zhu	Albert Gu	Sijie Yan	Dosovitskiy, A. et al.
種類	Neural network architecture	Neural network architecture	Neural network architecture	Transformer architecture for images (self-attention over patches)
原典	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.	Gu, A., & Dao, C. (2023). Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.08956.	Yan, S., Xiong, Y., & Lin, D. (2018). Spatial temporal graph convolutional networks for skeleton-based action recognition. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 32).	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
別名	ViM, Mamba for Vision	Mamba, State space models, Selective state space	ST-GCN, Spatial-Temporal Graph CNN	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
関連	4	4	4	5
概要	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.	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.	Spatial-Temporal Graph Convolutional Networks (ST-GCN) is an architecture introduced by Yan et al. in 2018 for skeleton-based action recognition. By modeling human skeletons as graphs where joints are nodes and bones are edges, ST-GCN applies graph convolutions across space and time to recognize actions from skeleton sequences.	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).