Mining GOLD Samples for Conditional GANs
Conditional generative adversarial networks (cGANs) have gained a considerable attention in recent years due to its class-wise controllability and superior quality for complex generation tasks. We introduce a simple yet effective approach to improving cGANs by measuring the discrepancy between the data distribution and the model distribution on given samples. The proposed measure, coined the gap of log-densities (GOLD), provides an effective self-diagnosis for cGANs while being efficienty computed from the discriminator. We propose three applications of the GOLD: example re-weighting, rejection sampling, and active learning, which improve the training, inference, and data selection of cGANs, respectively. Our experimental results demonstrate that the proposed methods outperform corresponding baselines for all three applications on different image datasets.
Code (1)
Tasks
Active LearningSimilar Papers 제목 키워드 기반
Mining Multi-Label Samples from Single Positive Labels
Conditional generative adversarial networks (cGANs) have shown superior results in class-conditional generation tasks. To simultaneously control multiple conditions, cGANs require multi-label training datasets, where mul…
Turning Waste into Wealth: Leveraging Low-Quality Samples for Enhancing Continuous Conditional Generative Adversarial Networks
Continuous Conditional Generative Adversarial Networks (CcGANs) enable generative modeling conditional on continuous scalar variables (termed regression labels). However, they can produce subpar fake images due to limite…
Data AugmentationDetecting Invasive Ductal Carcinoma with Semi-Supervised Conditional GANs
Invasive ductal carcinoma (IDC) comprises nearly 80% of all breast cancers. The detection of IDC is a necessary preprocessing step in determining the aggressiveness of the cancer, determining treatment protocols, and pre…
Predicting Patient OutcomesS2cGAN: Semi-Supervised Training of Conditional GANs with Fewer Labels
Generative adversarial networks (GANs) have been remarkably successful in learning complex high dimensional real word distributions and generating realistic samples. However, they provide limited control over the generat…
City-GAN: Learning architectural styles using a custom Conditional GAN architecture
Generative Adversarial Networks (GANs) are a well-known technique that is trained on samples (e.g. pictures of fruits) and which after training is able to generate realistic new samples. Conditional GANs (CGANs) addition…