Linganisha mbinu
Pitia mbinu ulizochagua bega kwa bega; safu zinazotofautiana zinaangaziwa.
| Modeli ya uenezaji inayojumuisha kikoa (Domain-Adaptive Diffusion Model)× | Transformer wa Maono unaobadilika na Kikoa× | |
|---|---|---|
| Nyanja | Ujifunzaji wa Kina | Ujifunzaji wa Kina |
| Familia | Machine learning | Machine learning |
| Mwaka wa asili≠ | 2022–2023 | 2021–2023 |
| Mwanzilishi≠ | Ho et al. (DDPM); domain-adaptation variants popularized by Gal et al. and Ruiz et al. (2022–2023) | Multiple groups (Yang et al., 2023; Xu et al., 2021; Ma et al., 2022) |
| Aina≠ | Generative model with domain adaptation | Domain adaptation + Vision Transformer ensemble |
| Chanzo asilia≠ | Ho, J., Jain, A., & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. Advances in Neural Information Processing Systems, 33, 6840–6851. link ↗ | 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 ↗ |
| Majina mbadala | DA-diffusion model, domain-adapted diffusion model, domain-adaptive DDPM, cross-domain diffusion model | DA-ViT, Domain Adaptation with Vision Transformer, ViT with Domain Adaptation, Domain-Adaptive ViT |
| Zinazohusiana≠ | 6 | 5 |
| Muhtasari≠ | A domain-adaptive diffusion model is a denoising diffusion probabilistic model (DDPM) that is pre-trained on large general datasets and then adapted — through fine-tuning, textual inversion, or LoRA — to generate high-quality outputs in a specific target domain. It combines the powerful generative capacity of diffusion models with domain adaptation techniques, enabling high-fidelity synthesis in specialized areas such as medical imaging, satellite imagery, or domain-specific art styles with limited target-domain data. | 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. |
| ScholarGateSeti ya data ↗ |
|
|