mlsanityData to 14 Oct 2026

Conditional Frechet Inception Distance

arXiv 2103.11521 ↗First posted 21 Mar 2021cs.LG cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

We consider distance functions between conditional distributions. We focus on the Wasserstein metric and its Gaussian case known as the Frechet Inception Distance (FID). We develop conditional versions of these metrics, analyze their relations and provide a closed form solution to the conditional FID (CFID) metric. We numerically compare the metrics in the context of performance evaluation of modern conditional generative models. Our results show the advantages of CFID compared to the classical FID and mean squared error (MSE) measures. In contrast to FID, CFID is useful in identifying failures where realistic outputs which are not related to their inputs are generated. On the other hand, compared to MSE, CFID is useful in identifying failures where a single realistic output is generated even though there is a diverse set of equally probable outputs.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 32 of its 45 references that are in the map. First posted on arXiv 21 Mar 2021.

Builds on

32 of 45 references.

References · 32

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  2. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  3. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  5. 2016Improved Techniques for Training GANscited by 2,970
  6. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  7. 2014Conditional Generative Adversarial Netscited by 2,162
  8. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  9. 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,234
  10. 2016Colorful Image Colorizationcited by 1,114
  11. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  12. 2017Unsupervised Image-to-Image Translation Networkscited by 603
20 more
  1. 2017Toward Multimodal Image-to-Image Translationcited by 296
  2. 2017Are GANs Created Equal? A Large-Scale Studycited by 267
  3. 2018cGANs with Projection Discriminatorcited by 254
  4. 2017StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 229
  5. 2016Unrolled Generative Adversarial Networkscited by 208
  6. 2018Fr'echet ChemNet Distance: A metric for generative models for molecules in drug discoverycited by 194
  7. 2019Effectively Unbiased FID and Inception Score and where to find themcited by 165
  8. 2019Classification Accuracy Score for Conditional Generative Modelscited by 136
  9. 2016Mode Regularized Generative Adversarial Networkscited by 123
  10. 2018Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Datacited by 76
  11. 2019HYPE: A Benchmark for Human eYe Perceptual Evaluation of Generative Modelscited by 59
  12. 2019Unsupervised Medical Image Translation Using Cycle-MedGANcited by 44
  13. 2019Explorable Super Resolutioncited by 44
  14. 2018An Improved Evaluation Framework for Generative Adversarial Networkscited by 26
  15. 2019On the Evaluation of Conditional GANscited by 21
  16. 2020Evaluation Metrics for Conditional Image Generationcited by 19
  17. 2020Direct Speech-to-image Translationcited by 12
  18. 2019Subsampling Generative Adversarial Networks: Density Ratio Estimation in Feature Space with Softplus Losscited by 11
  19. 2020The Surprising Effectiveness of Linear Unsupervised Image-to-Image Translationcited by 5
  20. 2019PI-REC: Progressive Image Reconstruction Network With Edge and Color Domaincited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 3; 2023: 2; 2024: 5; 2025: 3; 2026: 2.

16 papers.

Sort:

By area:

  1. 2024Learning Flow Fields in Attention for Controllable Person Image Generationcited by 27
  2. 2021Evaluating generative networks using Gaussian mixtures of image featurescited by 11
  3. 2023A Conditional Normalizing Flow for Accelerated Multi-Coil MR Imagingcited by 10
  4. 2022A Regularized Conditional GAN for Posterior Sampling in Image Recovery Problemscited by 9
  5. 2022Semantics-Empowered Communication: A Tutorial-cum-Surveycited by 8
  6. 2025Learning few-step posterior samplers by unfolding and distillation of diffusion modelscited by 6
  7. 2024A Unified Module for Accelerating STABLE-DIFFUSION: LCM-LORAcited by 3
  8. 2022SSD: Towards Better Text-Image Consistency Metric in Text-to-Image Generationcited by 2
  9. 2024DiffLoss: unleashing diffusion model as constraint for training image restoration networkcited by 2
  10. 2024pcaGAN: Improving Posterior-Sampling cGANs via Principal Component Regularizationcited by 2
  11. 2024Diff-GOn: Enhancing Diffusion Models for Goal-Oriented Communicationscited by 2
  12. 2025Cross-Modal Diffusion for Biomechanical Dynamical Systems Through Local Manifold Alignmentcited by 1
4 more
  1. 2023Counterfactual Edits for Generative Evaluationcited by 0
  2. 2025Evaluating Text-to-Image and Text-to-Video Synthesis with a Conditional Fr'echet Distancecited by 0
  3. 2026A Proper Scoring Rule for Virtual Stainingcited by 0
  4. 2026ReSAGE-PAR: Representational Similarity Assessment for Generative Expansion in Pedestrian Attribute Recognitioncited by 0