方法对比

	掩码自编码器	潜在扩散模型	SimCLR	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	2021	2022	2020	2021
提出者	Kaiming He	Robin Rombach	Ting Chen	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	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).	Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 10684-10695).	Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A simple framework for contrastive learning of visual representations. In International conference on machine learning (pp. 1597-1607). PMLR.	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
别名	MAE, Vision MAE	LDM, Stable Diffusion, Latent Diffusion	Simple contrastive learning, SimCLR framework	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
相关	4	4	4	5
摘要	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.	Latent Diffusion Models (LDMs) are a generative approach introduced by Rombach et al. in 2022 that performs the diffusion process in a compressed latent space rather than pixel space, enabling efficient high-resolution image synthesis. By compressing images into a low-dimensional latent representation using a variational autoencoder, diffusion becomes computationally tractable while maintaining visual quality.	SimCLR is a self-supervised learning framework introduced by Chen et al. in 2020 that learns visual representations by contrasting similar and dissimilar views of images. The method applies strong data augmentations to create different views of the same image, then trains an encoder to bring similar views close in representation space while pushing dissimilar views apart.	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).