Krahasoni metodat

	Vision Transformer i Përshtatshëm për Domene (DA-ViT)	Klasifikimi i bazuar në BERT të përshtatur me domen
Fusha	Mësimi i thellë	Mësimi i thellë
Familja	Machine learning	Machine learning
Viti i origjinës	2021–2023	2019–2020
Krijuesi	Multiple groups (Yang et al., 2023; Xu et al., 2021; Ma et al., 2022)	Gururangan et al. (2020); earlier domain-specific instances include Lee et al. (2020) — BioBERT
Lloji	Domain adaptation + Vision Transformer ensemble	Domain-adaptive pre-training followed by supervised fine-tuning
Burimi themelues	Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., ... & Houlsby, N. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. International Conference on Learning Representations (ICLR).	Gururangan, S., Marasovic, A., Swayamdipta, S., Lo, K., Beltagy, I., Downey, D., & Smith, N. A. (2020). Don't Stop Pretraining: Adapt Language Models to Domains and Tasks. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020), 8342–8360.
Emërtime të tjera	DA-ViT, Domain Adaptation with Vision Transformer, ViT with Domain Adaptation, Domain-Adaptive ViT	DAPT BERT classification, domain-adaptive pre-training, domain-specific BERT fine-tuning, BERT DAPT
Të lidhura	5	6
Përmbledhja	Domain-Adaptive Vision Transformer (DA-ViT) applies domain adaptation techniques — such as adversarial alignment, self-training, or attention-level bridging — on top of a pretrained Vision Transformer backbone to transfer visual knowledge from a labeled source domain to an unlabeled or lightly labeled target domain, reducing the distribution shift that limits standard ViT fine-tuning.	Domain-adaptive BERT-based classification extends the standard fine-tuning pipeline by first continuing BERT's masked-language-model pre-training on a large corpus of in-domain unlabeled text, then fine-tuning the adapted model on labeled examples for the target classification task. This two-stage approach closes the vocabulary and distributional gap between BERT's general pre-training corpus and specialized domains such as biomedicine, law, finance, or social-media text.