Corpus ID: 216553817

Evaluation Metrics for Conditional Image Generation

@article{Benny2020EvaluationMF,
  title={Evaluation Metrics for Conditional Image Generation},
  author={Yaniv Benny and T. Galanti and Sagie Benaim and L. Wolf},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.12361}
}
  • Yaniv Benny, T. Galanti, +1 author L. Wolf
  • Published 2020
  • Computer Science
  • 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 Frechet 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… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 30 REFERENCES
    Analyzing and Improving the Image Quality of StyleGAN
    168
    A Style-Based Generator Architecture for Generative Adversarial Networks
    1054
    Image Generation from Scene Graphs
    216
    Progressive Growing of GANs for Improved Quality, Stability, and Variation
    1979
    cGANs with Projection Discriminator
    282
    Improved Techniques for Training GANs
    3455
    Large Scale GAN Training for High Fidelity Natural Image Synthesis
    1107
    AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
    356
    Conditional Generative Adversarial Nets
    3432
    Generative Adversarial Nets
    16955