ScholarGate
Asistent

Porovnať metódy

Prezrite si vybrané metódy vedľa seba; riadky, ktoré sa líšia, sú zvýraznené.

Adaptívny ViT pre doménu×Doménovo-adaptívna klasifikácia založená na modeli BERT×
OdborHlboké učenieHlboké učenie
RodinaMachine learningMachine learning
Rok vzniku2021–20232019–2020
TvorcaMultiple 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
TypDomain adaptation + Vision Transformer ensembleDomain-adaptive pre-training followed by supervised fine-tuning
Pôvodný zdrojDosovitskiy, 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 ↗
Ďalšie názvyDA-ViT, Domain Adaptation with Vision Transformer, ViT with Domain Adaptation, Domain-Adaptive ViTDAPT BERT classification, domain-adaptive pre-training, domain-specific BERT fine-tuning, BERT DAPT
Príbuzné56
ZhrnutieDomain-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.
ScholarGateDátová sada
  1. v1
  2. 2 Zdroje
  3. PUBLISHED
  1. v1
  2. 2 Zdroje
  3. PUBLISHED

Prejsť na hľadanie Stiahnuť snímky

ScholarGatePorovnať metódy: Domain-adaptive vision transformer · Domain-adaptive BERT-based Classification. Získané 2026-06-18 z https://scholargate.app/sk/compare