So sánh phương pháp

	Mô hình khuếch tán giám sát yếu	Mô hình khuếch tán tự giám sát
Lĩnh vực	Học sâu	Học sâu
Họ	Machine learning	Machine learning
Năm ra đời	2022–2024	2020–2022
Người khởi xướng	Ho et al. (DDPM foundation); weak supervision integration by multiple groups, 2022–2024	Ho, J. et al.; extended by Chen, T. et al. and subsequent self-supervised diffusion works
Loại	Generative model with imperfect supervision	Generative model with self-supervised representation objective
Công trình gốc	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. Advances in Neural Information Processing Systems (NeurIPS), 33, 6840–6851.
Tên gọi khác	WS-Diffusion, weakly supervised DDPM, label-efficient diffusion model, noisy-label diffusion training	SSDM, self-supervised score-based model, diffusion-based self-supervised learning, denoising diffusion with self-supervised pretraining
Liên quan	6	2
Tóm tắt	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 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.