方法对比

	Mamba（状态空间模型）	掩码自编码器	神经辐射场 (NeRF)	Vision Transformer
领域	深度学习	深度学习	深度学习	深度学习
方法族	Machine learning	Machine learning	Machine learning	Machine learning
起源年份	2023	2021	2020	2021
提出者	Albert Gu	Kaiming He	Ben Mildenhall	Dosovitskiy, A. et al.
类型	Neural network architecture	Neural network architecture	Neural network architecture	Transformer architecture for images (self-attention over patches)
开创性文献	Gu, A., & Dao, C. (2023). Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.08956.	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).	Mildenhall, B., Srinivasan, P. P., Tancik, M., Barron, J. T., Ramamoorthi, R., & Ng, R. (2020). NeRF: Representing scenes as neural radiance fields for view synthesis. In Computer Vision-ECCV 2020: 16th European Conference (pp. 405-421). Springer International Publishing.	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
别名	Mamba, State space models, Selective state space	MAE, Vision MAE	NeRF, Neural radiance field	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
相关	4	4	4	5
摘要	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.	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.	Neural Radiance Fields (NeRF) is a method introduced by Mildenhall et al. in 2020 that represents a 3D scene as a continuous function parameterized by a neural network. Given multi-view images of a scene, NeRF learns to predict the color and density of light rays at any spatial location and viewing angle, enabling novel view synthesis with photorealistic quality.	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).