Measuring Mode Collapse: Comparative Study Between Architectures Gan

Generative Adversarial Networks (GANs) are a type of generative model widely used in various applications, but they often suffer from a common problem called mode collapse. This phenomenon occurs when the generator learns to produce only a small group of images instead of diverse ones. Mode collapse can occur for two reasons: firstly, when the discriminator becomes so effective that the generator can no longer learn, and secondly, when the generator finds a way to deceive the discriminator with a small number of samples, causing it to lack the motivation to diversify its outputs. This study evaluates multiple GAN-based models with various metrics that measure mode collapse. The behavior of models with similar parameters is analyzed.