Comparer des méthodes

	Embeddings BERT	Vision Transformer
Domaine	Fouille de textes	Apprentissage profond
Famille	Process / pipeline	Machine learning
Année d'origine	2019	2021
Auteur d'origine	Devlin, Chang, Lee & Toutanova (Google AI)	Dosovitskiy, A. et al.
Type	Contextual transformer text-representation method	Transformer architecture for images (self-attention over patches)
Source fondatrice	Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL-HLT, 4171-4186.	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Alias	contextual embeddings, transformer embeddings, BERT Tabanlı Metin Gömülmeleri	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Apparentées	4	5
Résumé	BERT-based text embeddings, introduced by Devlin and colleagues at Google AI in 2019, turn text into context-sensitive dense vectors using a bidirectional Transformer encoder. Because the meaning of a word shifts with its context, BERT produces richer representations than static methods such as Word2Vec or topic models like LDA.	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).