Linganisha mbinu
Pitia mbinu ulizochagua bega kwa bega; safu zinazotofautiana zinaangaziwa.
| Modeli ya uenezaji inayojumuisha kikoa (Domain-Adaptive Diffusion Model)× | Muundo wa Uenezaji wa Kujifundisha× | |
|---|---|---|
| Nyanja | Ujifunzaji wa Kina | Ujifunzaji wa Kina |
| Familia | Machine learning | Machine learning |
| Mwaka wa asili≠ | 2022–2023 | 2020–2022 |
| Mwanzilishi≠ | Ho et al. (DDPM); domain-adaptation variants popularized by Gal et al. and Ruiz et al. (2022–2023) | Ho, J. et al.; extended by Chen, T. et al. and subsequent self-supervised diffusion works |
| Aina≠ | Generative model with domain adaptation | Generative model with self-supervised representation objective |
| Chanzo asilia≠ | Ho, J., Jain, A., & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. Advances in Neural Information Processing Systems, 33, 6840–6851. link ↗ | Ho, J., Jain, A., & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. Advances in Neural Information Processing Systems (NeurIPS), 33, 6840–6851. link ↗ |
| Majina mbadala | DA-diffusion model, domain-adapted diffusion model, domain-adaptive DDPM, cross-domain diffusion model | SSDM, self-supervised score-based model, diffusion-based self-supervised learning, denoising diffusion with self-supervised pretraining |
| Zinazohusiana≠ | 6 | 2 |
| 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. | A self-supervised diffusion model couples the iterative noise-and-denoise generative process of denoising diffusion probabilistic models with a self-supervised representation learning objective — such as contrastive or masked prediction loss — so that the model simultaneously learns to generate realistic data and to produce semantically meaningful representations without any labeled examples. |
| ScholarGateSeti ya data ↗ |
|
|