Differentially Private Denoise Diffusion Probability Models
Diffusion models and their variants have achieved high-quality image generation without adversarial training. These algorithms provide new ideas for data shortages in some fields. But the diffusion model also faces the same problem as other generative models: the learned probability density function...
| الحاوية / القاعدة: | IEEE Access |
|---|---|
| المؤلفون الرئيسيون: | , , , , |
| التنسيق: | مقال |
| اللغة: | الإنجليزية |
| منشور في: |
IEEE
2023-01-01
|
| الموضوعات: | |
| الوصول للمادة أونلاين: | https://ieeexplore.ieee.org/document/10251532/ |