방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 약지도 GAN× | 준지도 학습 GAN× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2014–2017 | 2016 |
| 창시자≠ | Odena et al.; building on Goodfellow et al. (2014) | Odena, A.; Salimans, T. et al. |
| 유형≠ | Generative model with weak supervision | Semi-supervised generative model |
| 원전≠ | 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. link ↗ | Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016). Improved Techniques for Training GANs. Advances in Neural Information Processing Systems (NeurIPS), 29. link ↗ |
| 별칭 | WS-GAN, weakly supervised generative adversarial network, label-efficient GAN, semi-labeled GAN | SGAN, Semi-GAN, semi-supervised generative adversarial network, GAN-based semi-supervised learning |
| 관련 | 5 | 5 |
| 요약≠ | 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. | Semi-supervised GAN (SGAN) extends the standard GAN discriminator to simultaneously classify labeled examples into K real classes and detect generated fakes as a (K+1)-th class, letting the generator's synthetic data act as implicit regularization and allowing strong classifiers to be trained with very few labeled examples. |
| ScholarGate데이터셋 ↗ |
|
|