Порівняння методів

	Модель дифузії зі слабким наглядом	Дифузійна модель
Галузь	Глибоке навчання	Глибоке навчання
Родина	Machine learning	Machine learning
Рік появи	2022–2024	2020
Автор методу	Ho et al. (DDPM foundation); weak supervision integration by multiple groups, 2022–2024	Ho, J., Jain, A. & Abbeel, P.
Тип	Generative model with imperfect supervision	Generative deep learning (denoising diffusion)
Основоположне джерело	Ho, J., Jain, A., & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. Advances in Neural Information Processing Systems (NeurIPS), 33, 6840–6851.	Ho, J., Jain, A. & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. NeurIPS.
Інші назви	WS-Diffusion, weakly supervised DDPM, label-efficient diffusion model, noisy-label diffusion training	Difüzyon Modeli (DDPM / Stable Diffusion), difüzyon modeli, denoising diffusion model, DDPM
Пов'язані	6	4
Підсумок	A weakly supervised diffusion model trains or conditions a denoising diffusion probabilistic model using coarse, noisy, or incomplete supervision signals — such as image-level class labels, bounding boxes, or crowd-sourced annotations — instead of pixel-precise ground truth. This allows high-quality generative and discriminative outputs in annotation-scarce settings where full labeling is infeasible or prohibitively expensive.	A diffusion model is a generative deep-learning method, introduced by Ho, Jain and Abbeel in 2020 (DDPM), that learns to produce high-quality images, audio and molecular structures by reversing a step-by-step noising process. It has largely displaced GANs as the current state of the art in generative modelling.