ScholarGate
Асистент

Порівняння методів

Переглядайте обрані методи поруч; рядки з відмінностями підсвічено.

Самокеровані дифузійні моделі×Генеративно-змагальна мережа×
ГалузьГлибоке навчанняГлибоке навчання
РодинаMachine learningMachine learning
Рік появи2020–20222014
Автор методуHo, J. et al.; extended by Chen, T. et al. and subsequent self-supervised diffusion worksGoodfellow, I. et al.
ТипGenerative model with self-supervised representation objectiveGenerative deep learning (adversarial two-network game)
Основоположне джерелоHo, J., Jain, A., & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. Advances in Neural Information Processing Systems (NeurIPS), 33, 6840–6851. link ↗Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS. link ↗
Інші назвиSSDM, self-supervised score-based model, diffusion-based self-supervised learning, denoising diffusion with self-supervised pretrainingÜretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network
Пов'язані24
ПідсумокA 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.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.
ScholarGateНабір даних
  1. v1
  2. 2 Джерела
  3. PUBLISHED
  1. v1
  2. 2 Джерела
  3. PUBLISHED

Перейти до пошуку Download slides

ScholarGateПорівняння методів: Self-supervised Diffusion Model · Generative Adversarial Network. Отримано 2026-06-15 з https://scholargate.app/uk/compare