Comparison of Frchet-based and Perceptual Metrics for Detecting Mode Collapse in Large-Scale Multimodal Generative Models

Abstract We present two new metrics for evaluating generative models in the class-conditional image generation setting. These metrics are obtained by generalizing the two most popular unconditional metrics: the Inception Score (IS) and the Frchet Inception Distance (FID). A theoretical analysis shows the motivation behind each proposed metric and links the novel metrics to their unconditional counterparts. The link takes the form of a product in the case of IS or an upper bound in the FID case. We provide an extensive empirical evaluation, comparing the metrics to their unconditional variants

Research goal: How do Fréchet-based metrics compare to perceptual metrics in detecting mode collapse for large-scale multimodal generative models?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.8/10.