Сравнение на методи
Прегледайте избраните методи един до друг; редовете с разлики са откроени.
| Полу-наблюдаван дифузионен модел× | Генеративна състезателна мрежа× | |
|---|---|---|
| Област | Дълбоко обучение | Дълбоко обучение |
| Семейство | Machine learning | Machine learning |
| Година на възникване≠ | 2020–2022 | 2014 |
| Създател≠ | Multiple groups (Ho et al., Song et al., and successors) | Goodfellow, I. et al. |
| Тип≠ | Generative model with semi-supervised guidance | Generative deep learning (adversarial two-network game) |
| Основополагащ източник≠ | Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., & Ganguli, S. (2015). Deep Unsupervised Learning using Nonequilibrium Thermodynamics. Proceedings of the 32nd International Conference on Machine Learning (ICML), 2256–2265. link ↗ | Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS. link ↗ |
| Други названия | Semi-supervised DDPM, Label-guided diffusion model, Semi-supervised score-based generative model, SSL diffusion | Üretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network |
| Свързани≠ | 3 | 4 |
| Резюме≠ | A semi-supervised diffusion model extends the denoising diffusion probabilistic framework to settings where only a fraction of training samples carry class labels. By combining an unconditional diffusion backbone with a lightweight classifier trained on labeled examples, it learns to generate high-quality, label-conditioned outputs while still exploiting the structure in unlabeled data. | A Generative Adversarial Network (GAN), introduced by Ian Goodfellow and colleagues in 2014, produces realistic synthetic data through the competition of two neural networks — a generator and a discriminator. It is widely used for image synthesis, data augmentation, and distribution estimation. |
| ScholarGateНабор от данни ↗ |
|
|