Vertaile menetelmiä

	Heikosti ohjattu diffuusiomalli	Puolivalvottu diffuusiomalli
Tieteenala	Syväoppiminen	Syväoppiminen
Menetelmäperhe	Machine learning	Machine learning
Syntyvuosi	2022–2024	2020–2022
Kehittäjä	Ho et al. (DDPM foundation); weak supervision integration by multiple groups, 2022–2024	Multiple groups (Ho et al., Song et al., and successors)
Tyyppi	Generative model with imperfect supervision	Generative model with semi-supervised guidance
Alkuperäislähde	Ho, J., Jain, A., & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. Advances in Neural Information Processing Systems (NeurIPS), 33, 6840–6851.	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.
Rinnakkaisnimet	WS-Diffusion, weakly supervised DDPM, label-efficient diffusion model, noisy-label diffusion training	Semi-supervised DDPM, Label-guided diffusion model, Semi-supervised score-based generative model, SSL diffusion
Liittyvät	6	3
Tiivistelmä	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 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.