手法を比較

	マルチモーダルBERTベース分類	ビジョントランスフォーマー
分野	深層学習	深層学習
系統	Machine learning	Machine learning
提唱年	2019	2021
提唱者	Kiela, D. et al.; Lu, J. et al.	Dosovitskiy, A. et al.
種類	Multimodal transformer classifier	Transformer architecture for images (self-attention over patches)
原典	Kiela, D., Bhooshan, S., Firooz, H., Perez, E., & Testuggine, D. (2019). Supervised multimodal bitransformers for classifying images and text. arXiv preprint arXiv:1909.02950.	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
別名	MMBT, multimodal transformer classification, BERT multimodal fusion, vision-language BERT classifier	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
関連	2	5
概要	Multimodal BERT-based classification extends the BERT transformer architecture to jointly encode and classify data from multiple modalities — most commonly text paired with images — by fusing their representations before a final classification head. Introduced prominently around 2019 through models such as MMBT and ViLBERT, it has become a standard approach for tasks where neither text nor image alone carries sufficient information for accurate labeling.	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).