手法を比較

	マスク化オートエンコーダ	Segment Anything Model	Swin Transformer	Vision Mamba
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	2021	2023	2021	2024
提唱者	Kaiming He	Alexander Kirillov	Ze Liu	Li Zhu
種類	Neural network architecture	Neural network architecture	Neural network architecture	Neural network architecture
原典	He, K., Chen, X., Xie, S., Li, Y., Dollár, P., & Girshick, R. (2022). Masked autoencoders are scalable vision learners. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 16000-16009).	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).	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.
別名	MAE, Vision MAE	SAM, Segment Anything	Swin, Hierarchical Vision Transformer	ViM, Mamba for Vision
関連	4	4	4	4
概要	Masked Autoencoders (MAE) is a self-supervised learning approach introduced by He et al. in 2021 that masks random patches of an image and trains a model to reconstruct the missing content. Adapting the masked language modeling paradigm from NLP to vision, MAE learns rich visual representations by solving a challenging reconstruction task without requiring labels.	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.	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.