Сравнение методов

	Transfer Learning GAN	Трансферное обучение с диффузионной моделью
Область	Глубокое обучение	Глубокое обучение
Семейство	Machine learning	Machine learning
Год появления	2014–2018	2020–2023
Автор метода	Goodfellow, I. et al. (GAN); Wang & Ramanan (transfer to GAN)	Ho et al. (DDPM); transfer application popularized by Rombach et al. (Stable Diffusion) and Ruiz et al. (DreamBooth), 2020–2023
Тип	Generative model with transferred weights	Generative model with transfer learning
Основополагающий источник	Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A. & Bengio, Y. (2014). Generative Adversarial Nets. Advances in Neural Information Processing Systems (NeurIPS), 27, 2672–2680.	Ho, J., Jain, A., & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. Advances in Neural Information Processing Systems (NeurIPS), 33, 6840–6851.
Другие названия	TL-GAN, pretrained GAN, GAN fine-tuning, domain-adaptive GAN	diffusion model fine-tuning, pre-trained diffusion transfer, TL-DM, domain-adapted diffusion model
Связанные	6	5
Сводка	Transfer Learning GAN initialises a Generative Adversarial Network — or both its generator and discriminator — from weights pretrained on a large source dataset, then fine-tunes the network on a smaller target dataset. This approach allows high-quality generative modelling even when target-domain data are scarce, by reusing low- and mid-level feature representations learned at scale.	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.