Uporedite metode

	Доменски-адаптивни Трансформер	Transferno učenje	Vision Transformer
Oblast	Duboko učenje	Mašinsko učenje	Duboko učenje
Porodica	Machine learning	Machine learning	Machine learning
Godina nastanka	2019–2022	2010 (formalized); 1990s (early roots)	2021
Tvorac	Various (Vaswani et al. 2017 for Transformers; domain adaptation extensions emerged 2019–2022)	Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)	Dosovitskiy, A. et al.
Tip	Pre-trained model fine-tuned with domain-shift adaptation	Learning paradigm	Transformer architecture for images (self-attention over patches)
Temeljni izvor	Ni, J., Hernandez Abrego, G., Constant, N., Ma, J., Hall, K., Cer, D., & Yang, Y. (2021). Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models. Findings of ACL 2022. arXiv:2108.08877.	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Drugi nazivi	DAT, domain-adaptive Transformer, domain adaptation with Transformers, transfer-learning Transformer	TL, domain adaptation, fine-tuning, pre-trained model adaptation	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Srodne	2	3	5
Sažetak	A Domain-Adaptive Transformer (DAT) is a Transformer-based model — such as BERT or ViT — extended with an explicit domain-alignment objective so that learned representations transfer well from a labeled source domain to a different, often unlabeled, target domain. The approach combines the powerful representation capacity of Transformers with domain adaptation techniques such as adversarial training or contrastive alignment to minimise domain shift.	Transfer learning is a machine learning paradigm in which knowledge gained from training a model on a source task or domain is reused to improve learning on a different but related target task or domain. It is especially powerful when labeled data for the target task is scarce, and it underlies most modern deep learning applications in computer vision, natural language processing, and beyond.	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).