Porovnat metody

	Víceúčelová klasifikace založená na BERT	CLIP	Vision Transformer
Obor	Hluboké učení	Hluboké učení	Hluboké učení
Rodina	Machine learning	Machine learning	Machine learning
Rok vzniku	2019	2021	2021
Tvůrce	Kiela, D. et al.; Lu, J. et al.	Radford, A.; Kim, J. W.; et al. (OpenAI)	Dosovitskiy, A. et al.
Typ	Multimodal transformer classifier	Contrastive vision-language pretraining model	Transformer architecture for images (self-attention over patches)
Původní zdroj	Kiela, D., Bhooshan, S., Firooz, H., Perez, E., & Testuggine, D. (2019). Supervised multimodal bitransformers for classifying images and text. arXiv preprint arXiv:1909.02950.	Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., & Sutskever, I. (2021). Learning Transferable Visual Models From Natural Language Supervision. Proceedings of the 38th International Conference on Machine Learning, PMLR 139, 8748–8763.	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Další názvy	MMBT, multimodal transformer classification, BERT multimodal fusion, vision-language BERT classifier	CLIP, Contrastive Language-Image Pre-training, zero-shot image classifier, visual-language model	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Příbuzné	2	2	5
Shrnutí	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.	CLIP (Contrastive Language-Image Pretraining) is a vision-language model introduced by Radford et al. at OpenAI in 2021 that jointly learns aligned image and text representations by training on 400 million internet-sourced image-text pairs using a contrastive objective, enabling zero-shot transfer to image classification tasks without any task-specific fine-tuning.	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).