Porovnať metódy

	Multimodálny Transformer	Klasifikácia obrazu
Odbor	Hlboké učenie	Hlboké učenie
Rodina	Machine learning	Machine learning
Rok vzniku	2019–2021	2012 (deep CNN era); conceptual roots 1989 (LeCun)
Tvorca	Lu et al. (ViLBERT); Radford et al. (CLIP)	Krizhevsky, A.; Sutskever, I.; Hinton, G. E.
Typ	Cross-modal attention-based deep learning model	Supervised classification task
Pôvodný zdroj	Lu, J., Batra, D., Parikh, D., & Lee, S. (2019). ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks. Advances in Neural Information Processing Systems (NeurIPS), 32.	Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems (NeurIPS), 25, 1097–1105.
Ďalšie názvy	multimodal attention model, cross-modal transformer, vision-language transformer, multi-modal fusion transformer	visual classification, image recognition, CNN-based classification, visual categorization
Príbuzné	5	5
Zhrnutie	A Multimodal Transformer extends the standard Transformer architecture to process and jointly reason over two or more input modalities — most commonly text and images, but also audio, video, or structured data. Cross-modal attention layers allow information from one modality to inform representations in another, enabling tasks such as visual question answering, image captioning, and multimodal sentiment analysis.	Image classification is the task of assigning a single semantic label to an entire image from a fixed set of categories. Modern approaches rely on deep convolutional neural networks (CNNs) or Vision Transformers (ViTs) trained end-to-end on large labeled datasets such as ImageNet, achieving superhuman accuracy on many benchmarks and underpinning applications from medical imaging to autonomous vehicles.