Сравнение на методи
Прегледайте избраните методи един до друг; редовете с разлики са откроени.
| Адаптивен към домейна визуален трансформер× | Адаптивно към домейна класифициране, базирано на BERT× | |
|---|---|---|
| Област | Дълбоко обучение | Дълбоко обучение |
| Семейство | Machine learning | Machine learning |
| Година на възникване≠ | 2021–2023 | 2019–2020 |
| Създател≠ | 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 |
| Тип≠ | Domain adaptation + Vision Transformer ensemble | Domain-adaptive pre-training followed by supervised fine-tuning |
| Основополагащ източник≠ | 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). link ↗ | 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. DOI ↗ |
| Други названия | 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 |
| Свързани≠ | 5 | 6 |
| Резюме≠ | 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. |
| ScholarGateНабор от данни ↗ |
|
|