mlsanityData to 7 Oct 2026

Evaluation Metrics for Conditional Image Generation

arXiv 2004.12361 ↗First posted 26 Apr 2020cs.CV cs.LG eess.IVcited by 18

Not on the map. Why?

Abstract (arXiv)

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 Fre'chet 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 and to other metrics, and utilize them to analyze existing generative models, thus providing additional insights about their performance, from unlearned classes to mode collapse.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 2; 2023: 7; 2024: 4; 2025: 0; 2026: 3.

18 papers.

Sort:

By area:

  1. 2023Conditional Image-to-Video Generation with Latent Flow Diffusion Modelscited by 180
  2. 2024Time Weaver: A Conditional Time Series Generation Modelcited by 35
  3. 2022FlexIT: Towards Flexible Semantic Image Translationcited by 28
  4. 2023Diffusion Illusions: Hiding Images in Plain Sightcited by 26
  5. 2023Beyond Statistical Similarity: Rethinking Metrics for Deep Generative Models in Engineering Designcited by 22
  6. 2023Image-Based Virtual Try-On: A Surveycited by 19
  7. 2021Divergence Frontiers for Generative Models: Sample Complexity, Quantization Effects, and Frontier Integralscited by 18
  8. 2021Conditional Frechet Inception Distancecited by 16
  9. 2023Semantic Communications for Artificial Intelligence Generated Content (AIGC) Toward Effective Content Creationcited by 8
  10. 2024Elucidating the design space of language models for image generationcited by 6
  11. 2026Manifold-Aware Perturbations for Constrained Generative Modelingcited by 2
  12. 2022Generative Models with Information-Theoretic Protection Against Membership Inference Attackscited by 1
6 more
  1. 2024Disentangling Mean Embeddings for Better Diagnostics of Image Generatorscited by 1
  2. 2023Counterfactual Edits for Generative Evaluationcited by 0
  3. 2023DPAF: Image Synthesis via Differentially Private Aggregation in Forward Phasecited by 0
  4. 2024Conditional Idempotent Generative Networkscited by 0
  5. 2026Conformal Reliability: A New Evaluation Metric for Conditional Generationcited by 0
  6. 2026What FID Hides: Detecting, Ranking, and Diagnosing Deviations in Generative Evaluationcited by 0