Порівняння методів

	Трансформер для комп'ютерного зору	Варіаційний автокодувальник
Галузь	Глибоке навчання	Глибоке навчання
Родина	Machine learning	Machine learning
Рік появи	2021	2014
Автор методу	Dosovitskiy, A. et al.	Kingma, D. P. & Welling, M.
Тип	Transformer architecture for images (self-attention over patches)	Deep generative latent-variable model (encoder–decoder)
Основоположне джерело	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.	Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR).
Інші назви	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images	Değişkensel Otokodlayıcı (VAE), VAE, auto-encoding variational Bayes, deep latent variable model
Пов'язані	5	5
Підсумок	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).	The Variational Autoencoder (VAE) is a deep generative latent-variable model, introduced by Diederik Kingma and Max Welling in 2014, that encodes data as a probability distribution in a latent space and samples from that distribution to generate new examples. It is used for data generation, anomaly detection, and feature learning.