Modern metrics for generative learning like Fréchet Inception Distance (FID) demonstrate impressive performance. However, they suffer from various shortcomings, like a bias towards specific generators and datasets. To address this problem, we propose the Fréchet Wavelet Distance (FWD) as a domain-agnostic metric based on Wavelet Packet Transform (Wp). FWD provides a sight across a broad spectrum of frequencies in images with a high resolution, along with preserving both spatial and textural aspects. Specifically, we use Wp to project generated and dataset images to packet coefficient space. Further, we compute Fréchet distance with the resultant coefficients to evaluate the quality of a generator. This metric is general-purpose and dataset-domain agnostic, as it does not rely on any pre-trained network while being more interpretable because of frequency band transparency. We conclude with an extensive evaluation of a wide variety of generators across various datasets that the proposed FWD is able to generalize and improve robustness to domain shift and various corruptions compared to other metrics.
Citation:
L. Veeramacheneni, M. Wolter, and J. Gall, “Frechet Wavelet Distance: A Domain-Agnostic Metric for Image Generation,” arXiv (Cornell University), Jan. 2023, doi: 10.48550/arxiv.2312.15289.
More Information:
Open source: https://doi.org/10.48550/arXiv.2312.15289
