<ul><li>There is significant current research focused on determining meaningful evaluation metrics for generative models.</li><li>A unifying perspective is needed to allow for easier comparison and clearer explanation of metric benefits and drawbacks.</li><li>A class of kth-nearest-neighbors (kNN)-based metrics is unified under an information-theoretic lens.</li><li>A tri-dimensional metric composed of Precision Cross-Entropy (PCE), Recall Cross-Entropy (RCE), and Recall Entropy (RE) is proposed to measure fidelity and diversity.</li></ul>

A Unifying Information-theoretic Perspective on Evaluating Generative Models

Discover more