Порівняння методів

	Моделі прихованої дифузії	Mamba (модель на основі простору станів)	N-BEATSx	Трансформер для комп'ютерного зору
Галузь	Глибоке навчання	Глибоке навчання	Глибоке навчання	Глибоке навчання
Родина	Machine learning	Machine learning	Machine learning	Machine learning
Рік появи	2022	2023	2023	2021
Автор методу	Robin Rombach	Albert Gu	Cristian Challu	Dosovitskiy, A. et al.
Тип	Neural network architecture	Neural network architecture	Neural network architecture	Transformer architecture for images (self-attention over patches)
Основоположне джерело	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).	Gu, A., & Dao, C. (2023). Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.08956.	Challu, C., Olivares, K. Q., Oreshkin, B., Garza, F., Mergenthaler-Canseco, M., & Dubrawski, A. (2023). N-BEATSx: Neural Basis Expansion Analysis for Interpretable Time Series Forecasting. In ICLR 2023 Workshop on Multimodal Learning for Science (p. 4).	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Інші назви	LDM, Stable Diffusion, Latent Diffusion	Mamba, State space models, Selective state space	N-BEATSx, NBEATS-x	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Пов'язані	4	4	4	5
Підсумок	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.	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.	N-BEATSx is an extension of the N-BEATS neural time series forecasting model that incorporates exogenous (external) variables through a cross-learner architecture. Published in 2023, N-BEATSx improves upon N-BEATS by enabling the model to leverage additional features beyond the historical time series values.	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).