Сравнение на методи
Прегледайте избраните методи един до друг; редовете с разлики са откроени.
| Трансферно обучение с дифузионен модел× | Домейн-адаптивен дифузионен модел× | |
|---|---|---|
| Област | Дълбоко обучение | Дълбоко обучение |
| Семейство | Machine learning | Machine learning |
| Година на възникване≠ | 2020–2023 | 2022–2023 |
| Създател≠ | Ho et al. (DDPM); transfer application popularized by Rombach et al. (Stable Diffusion) and Ruiz et al. (DreamBooth), 2020–2023 | Ho et al. (DDPM); domain-adaptation variants popularized by Gal et al. and Ruiz et al. (2022–2023) |
| Тип≠ | Generative model with transfer learning | Generative model with domain adaptation |
| Основополагащ източник≠ | Ho, J., Jain, A., & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. Advances in Neural Information Processing Systems (NeurIPS), 33, 6840–6851. link ↗ | Ho, J., Jain, A., & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. Advances in Neural Information Processing Systems, 33, 6840–6851. link ↗ |
| Други названия | diffusion model fine-tuning, pre-trained diffusion transfer, TL-DM, domain-adapted diffusion model | DA-diffusion model, domain-adapted diffusion model, domain-adaptive DDPM, cross-domain diffusion model |
| Свързани≠ | 5 | 6 |
| Резюме≠ | Transfer Learning with Diffusion Models adapts a large pre-trained diffusion model — such as Stable Diffusion or DALL-E 2 — to a new target domain or task by continuing training on a smaller domain-specific dataset. Rather than learning the full generative process from scratch, practitioners leverage knowledge already encoded in millions of training steps to achieve high-quality domain-adapted generation with modest data and compute. | 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. |
| ScholarGateНабор от данни ↗ |
|
|