mlsanityData to 14 Oct 2026

Fr'echet Wavelet Distance: A Domain-Agnostic Metric for Image Generation

arXiv 2312.15289 ↗First posted 23 Dec 2023cs.CV cs.LG eess.IVcited by 9

Not on the map. Why?

Abstract (arXiv)

Modern metrics for generative learning like Fr'echet Inception Distance (FID) and DINOv2-Fr'echet Distance (FD-DINOv2) demonstrate impressive performance. However, they suffer from various shortcomings, like a bias towards specific generators and datasets. To address this problem, we propose the Fr'echet Wavelet Distance (FWD) as a domain-agnostic metric based on the Wavelet Packet Transform (Wp). FWD provides a sight across a broad spectrum of frequencies in images with a high resolution, preserving both spatial and textural aspects. Specifically, we use Wp to project generated and real images to the packet coefficient space. We then compute the Fr'echet 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 due to its ability to compute Fr'echet distance per packet, enhancing transparency. We conclude with an extensive evaluation of a wide variety of generators across various datasets that the proposed FWD can generalize and improve robustness to domain shifts and various corruptions compared to other metrics.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 43 of its 73 references that are in the map. First posted on arXiv 23 Dec 2023.

Builds on

43 of 73 references.

References · 43

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  7. 2022Scalable Diffusion Models with Transformerscited by 6,054
  8. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  9. 2017Neural Discrete Representation Learningcited by 4,712
  10. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  11. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  12. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
31 more
  1. 2016Improved Techniques for Training GANscited by 2,970
  2. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  3. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  4. 2018On the Spectral Bias of Neural Networkscited by 1,341
  5. 2021Palette: Image-to-Image Diffusion Modelscited by 1,300
  6. 2018Demystifying MMD GANscited by 1,293
  7. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  8. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 944
  9. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 516
  10. 2023Analyzing and Improving the Training Dynamics of Diffusion Modelscited by 402
  11. 2020Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributionscited by 280
  12. 2018A Note on the Inception Scorecited by 226
  13. 2023WIRE: Wavelet Implicit Neural Representationscited by 220
  14. 2022The Role of ImageNet Classes in Fr'echet Inception Distancecited by 213
  15. 2021Projected GANs Converge Fastercited by 208
  16. 2023Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion modelscited by 205
  17. 2019Photorealistic Style Transfer via Wavelet Transformscited by 166
  18. 2019Effectively Unbiased FID and Inception Score and where to find themcited by 165
  19. 2021StyleSwin: Transformer-based GAN for High-resolution Image Generationcited by 152
  20. 2019Fourier Spectrum Discrepancies in Deep Network Generated Imagescited by 139
  21. 2022Wavelet Diffusion Models are fast and scalable Image Generatorscited by 117
  22. 2018Human Motion Prediction via Spatio-Temporal Inpaintingcited by 114
  23. 2019SEN12MS -- A Curated Dataset of Georeferenced Multi-Spectral Sentinel-1/2 Imagery for Deep Learning and Data Fusioncited by 95
  24. 2022Wavelet Score-Based Generative Modelingcited by 62
  25. 2021On the Frequency Bias of Generative Modelscited by 60
  26. 2020Wavelet-Based Dual-Branch Network for Image Demoireingcited by 55
  27. 2018Attribute-aware Face Aging with Wavelet-based Generative Adversarial Networkscited by 34
  28. 2020Multi-level Wavelet-based Generative Adversarial Network for Perceptual Quality Enhancement of Compressed Videocited by 26
  29. 2021Wavelet-Packets for Deepfake Image Analysis and Detectioncited by 25
  30. 2023Markovian Sliced Wasserstein Distances: Beyond Independent Projectionscited by 11
  31. 2021Wavelet Transform-assisted Adaptive Generative Modeling for Colorizationcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 3.

9 papers.

  1. 2025Population-Aligned Persona Generation for LLM-based Social Simulationcited by 21
  2. 2024Boosting Latent Diffusion with Perceptual Objectivescited by 20
  3. 2025AR-RAG: Autoregressive Retrieval Augmentation for Image Generationcited by 3
  4. 2026WaiT for the Signal: Simple Frequency-Aware Flow-Matchingcited by 3
  5. 2025Solving Inverse Problems in Stochastic Self-Organizing Systems through Invariant Representationscited by 1
  6. 2025PRIVET: PRoximIty leakage detection Via Extreme value Theorycited by 1
  7. 2025Evaluating Text-to-Image and Text-to-Video Synthesis with a Conditional Fr'echet Distancecited by 0
  8. 2026APEX: Assumption-free Projection-based Embedding eXamination Metric for Generative Distribution Evaluationcited by 0
  9. 2026Decoding Register Tokens Preserves Global Scene Detailscited by 0