Comparar métodos

	GANs Fracamente Supervisionadas	Classificação de Imagens Fracamente Supervisionada
Área	Aprendizado profundo	Aprendizado profundo
Família	Machine learning	Machine learning
Ano de origem	2014–2017	2014–2016
Autor original	Odena et al.; building on Goodfellow et al. (2014)	Multiple contributors; class activation map approach: Zhou et al.
Tipo	Generative model with weak supervision	Weakly supervised deep learning paradigm
Fonte seminal	Odena, A., Olah, C., & Shlens, J. (2017). Conditional Image Synthesis with Auxiliary Classifier GANs. Proceedings of the 34th International Conference on Machine Learning (ICML), PMLR 70, 2642–2651.	Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016). Learning Deep Features for Discriminative Localization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2921–2929.
Outros nomes	WS-GAN, weakly supervised generative adversarial network, label-efficient GAN, semi-labeled GAN	WSL image classification, image-level supervised classification, noisy-label image classification, weakly labeled visual recognition
Relacionados	5	5
Resumo	A Weakly Supervised GAN is a generative adversarial network trained with partially labeled, noisily labeled, or coarse-annotation data instead of fully annotated ground truth. It extends the standard GAN framework so that limited supervision guides conditional generation or discriminative learning, enabling high-quality data synthesis and classification in label-scarce settings.	Weakly supervised image classification trains convolutional or transformer-based networks using only coarse, incomplete, or noisy supervision — such as image-level category labels, hashtags, or web-scraped tags — without requiring precise bounding boxes or pixel annotations. This dramatically reduces labeling cost while still enabling high-accuracy visual recognition at scale.