পদ্ধতির তুলনা করুন

	দুর্বলভাবে তত্ত্বাবধানে থাকা ডিফিউশন মডেল	জেনারেটিভ অ্যাডভারসারিয়াল নেটওয়ার্ক
ক্ষেত্র	গভীর শিখন	গভীর শিখন
পরিবার	Machine learning	Machine learning
উদ্ভবের বছর	2022–2024	2014
প্রবর্তক	Ho et al. (DDPM foundation); weak supervision integration by multiple groups, 2022–2024	Goodfellow, I. et al.
ধরন	Generative model with imperfect supervision	Generative deep learning (adversarial two-network game)
মৌলিক উৎস	Ho, J., Jain, A., & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. Advances in Neural Information Processing Systems (NeurIPS), 33, 6840–6851.	Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS.
অপর নাম	WS-Diffusion, weakly supervised DDPM, label-efficient diffusion model, noisy-label diffusion training	Üretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network
সম্পর্কিত	6	4
সারসংক্ষেপ	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 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.