mlsanityData to 14 Oct 2026

Unsupervised evaluation of GAN sample quality: Introducing the TTJac Score

arXiv 2309.00107 ↗First posted 31 Aug 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Evaluation metrics are essential for assessing the performance of generative models in image synthesis. However, existing metrics often involve high memory and time consumption as they compute the distance between generated samples and real data points. In our study, the new evaluation metric called the "TTJac score" is proposed to measure the fidelity of individual synthesized images in a data-free manner. The study first establishes a theoretical approach to directly evaluate the generated sample density. Then, a method incorporating feature extractors and discrete function approximation through tensor train is introduced to effectively assess the quality of generated samples. Furthermore, the study demonstrates that this new metric can be used to improve the fidelity-variability trade-off when applying the truncation trick. The experimental results of applying the proposed metric to StyleGAN 2 and StyleGAN 2 ADA models on FFHQ, AFHQ-Wild, LSUN-Cars, and LSUN-Horse datasets are presented. The code used in this research will be made publicly available online for the research community to access and utilize.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 30 references that are in the map. First posted on arXiv 31 Aug 2023.

Builds on

21 of 30 references.

References · 21

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  2. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  4. 2022Generative Adversarial Networkscited by 5,627
  5. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  6. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  7. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  8. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  9. 2018Demystifying MMD GANscited by 1,293
  10. 2020Training Generative Adversarial Networks with Limited Datacited by 1,186
  11. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,098
  12. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,039
9 more
  1. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 944
  2. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  3. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 695
  4. 2020GANSpace: Discovering Interpretable GAN Controlscited by 614
  5. 2020Unsupervised Discovery of Interpretable Directions in the GAN Latent Spacecited by 289
  6. 2019U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translationcited by 186
  7. 2022Rarity Score : A New Metric to Evaluate the Uncommonness of Synthesized Imagescited by 35
  8. 2021Feature Statistics Mixing Regularization for Generative Adversarial Networkscited by 9
  9. 2021Contrastive Fine-grained Class Clustering via Generative Adversarial Networkscited by 9

Built on by

Not cited yet.