Compara mètodes

	Autoencoders emmascarats	Models de difusió latents	SimCLR	Vision Transformer
Camp	Aprenentatge profund	Aprenentatge profund	Aprenentatge profund	Aprenentatge profund
Família	Machine learning	Machine learning	Machine learning	Machine learning
Any d'origen	2021	2022	2020	2021
Autor original	Kaiming He	Robin Rombach	Ting Chen	Dosovitskiy, A. et al.
Tipus	Neural network architecture	Neural network architecture	Neural network architecture	Transformer architecture for images (self-attention over patches)
Font seminal	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.
Àlies	MAE, Vision MAE	LDM, Stable Diffusion, Latent Diffusion	Simple contrastive learning, SimCLR framework	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Relacionats	4	4	4	5
Resum	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).