विधियों की तुलना करें

	कमजोर पर्यवेक्षित प्रसार मॉडल	दुर्बल पर्यवेक्षित सिमेंटिक सेगमेंटेशन
क्षेत्र	गहन अधिगम	गहन अधिगम
परिवार	Machine learning	Machine learning
उद्भव वर्ष	2022–2024	2014–2016
प्रवर्तक	Ho et al. (DDPM foundation); weak supervision integration by multiple groups, 2022–2024	Multiple contributors; Class Activation Mapping (Zhou et al., 2016) is foundational
प्रकार	Generative model with imperfect supervision	Pixel-level classification with image-level or coarse supervision
मौलिक स्रोत	Ho, J., Jain, A., & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. Advances in Neural Information Processing Systems (NeurIPS), 33, 6840–6851.	Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016). Learning Deep Features for Discriminative Localization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2921–2929.
उपनाम	WS-Diffusion, weakly supervised DDPM, label-efficient diffusion model, noisy-label diffusion training	WSSS, weak-label segmentation, image-level supervised segmentation, weakly-labeled pixel classification
संबंधित	6	4
सारांश	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.	Weakly Supervised Semantic Segmentation (WSSS) trains pixel-level scene parsers using only cheap, coarse annotations — typically image-level class tags — instead of costly dense pixel masks. By generating proxy pseudo-labels from a classification network (via Class Activation Maps or similar localisation cues) and iteratively refining them, WSSS brings full-supervision accuracy within reach at a fraction of the annotation cost.