So sánh phương pháp

	Mạng perceptron đa lớp thích ứng miền	Transformer Thích ứng Miền
Lĩnh vực	Học sâu	Học sâu
Họ	Machine learning	Machine learning
Năm ra đời	2006–2016	2019–2022
Người khởi xướng	Ben-David et al.; Ganin et al.	Various (Vaswani et al. 2017 for Transformers; domain adaptation extensions emerged 2019–2022)
Loại	Domain adaptation of feedforward neural network	Pre-trained model fine-tuned with domain-shift adaptation
Công trình gốc	Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., & Vaughan, J. W. (2010). A theory of learning from different domains. Machine Learning, 79(1–2), 151–175.	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.
Tên gọi khác	DA-MLP, domain-adaptive MLP, domain-adapted feedforward network, domain adaptation with MLP	DAT, domain-adaptive Transformer, domain adaptation with Transformers, transfer-learning Transformer
Liên quan	5	2
Tóm tắt	A domain-adaptive multilayer perceptron (DA-MLP) is a feedforward neural network trained to learn representations that are useful across a labeled source domain and an unlabeled or differently distributed target domain. By minimizing both a task loss and a domain-discrepancy objective, the MLP generalizes to the target domain with little or no target-domain labels.	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.