Measuring GAN Training in Real Time
Generative Adversarial Networks (GAN) are popular generative models of images. Although researchers proposed variants of GAN for different applications, evaluating and comparing GANs is still challenging as GANs may have many failure cases such as low visual quality and model collapse. To alleviate this issue, we propose a novel framework to evaluate the training stability (S), visual quality (Q), and mode diversity (D) of GAN simultaneously. SQD requires only a moderate number of samples, allowing real-time monitoring of the training dynamics of GAN. We showcase the utility of the SQD framework on prevalent GANs and discovered that the gradient penalty (Gulrajani et al., 2017) regularization significantly improves the performance of GAN. We also compare the gradient penalty regularization with other regularization methods and reveal that enforcing the 1-Lipschitz condition of the discriminator network stabilizes GAN training.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversitySimilar Papers 제목 키워드 기반
A Body Part Embedding Model With Datasets for Measuring 2D Human Motion Similarity
Human motion similarity is practiced in many fields, including action recognition, anomaly detection, and human performance evaluation. While many computer vision tasks have benefited from deep learning, measuring motion…
Action AnalysisAction RecognitionAnomaly DetectionUsing Kolmogorov-Smirnov Distance for Measuring Distribution Shift in Machine Learning
One of the major problems in Machine Learning (ML) and Artificial Intelligence (AI) is the fact that the probability distribution of the test data in the real world could deviate substantially from the probability distri…
Reinforcement LearningTo Measure or Not: A Cost-Sensitive, Selective Measuring Environment for Agricultural Management Decisions with Reinforcement Learning
Farmers rely on in-field observations to make well-informed crop management decisions to maximize profit and minimize adverse environmental impact. However, obtaining real-world crop state measurements is labor-intensive…
ManagementReinforcement Learning (RL)Real-time stress detection on social network posts using big data technology
In the context of modern life, particularly in Industry 4.0 within the online space, emotions and moods are frequently conveyed through social media posts. The trend of sharing stories, thoughts, and feelings on these pl…
EarthShift: a benchmark for measuring robustness to real-world distribution shifts in Earth observation
Current Earth observation benchmarks focus on measuring performance on diverse tasks and applications, typically measuring generalization in-distribution. But when models are deployed, they must generalize to myriad out-…