Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
Springer Nature Link
Log in

An Efficient and Rotation Invariant Fourier-Based Metric for Assessing the Quality of Images Created by Generative Models

  • Conference paper
  • First Online:
Bio-inspired Systems and Applications: from Robotics to Ambient Intelligence (IWINAC 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13259))

  • 1371 Accesses

Abstract

Recent progress in generative image modeling is leading to a new era of high-resolution fakes visually indistinguishable from real life images. However, the development of metrics capable of discerning whether images are synthetic or not runs behind the race of achieving the best generator, thus bringing potential threats. We propose a rotation invariant metric capable of distinguishing real and generated image datasets and we call it CSD (Circular Spectrum Distance) due to its circular nature and its inherent relation to the Fourier Spectrum. Its performance is analysed on a whole brain MRI dataset. CSD has similar behavior to FID during training but requires smaller batch sizes and is faster to compute.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 79.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 99.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Alt, H., Godau, M.: Computing the Frêchet distance between two poligonal curves. Int. J. Comput. Geom. Appli. (1995). https://doi.org/10.1142/s0218195995000064

    Article  MATH  Google Scholar 

  2. Borji, A.: Pros and cons of GAN evaluation measures. Comput. Vis. Image Underst. (2019). https://doi.org/10.1016/j.cviu.2018.10.009

    Article  Google Scholar 

  3. Cohen, T.S., Welling, M.: Group equivariant convolutional networks. In: 33rd International Conference on Machine Learning, ICML 2016, vol. 6, pp. 4375–4386, February 2016

    Google Scholar 

  4. Duque, P., Cuadra, J.M., Jiménez, E., Rincón-Zamorano, M.: Data preprocessing for automatic WMH segmentation with FCNNs. In: Ferrández Vicente, J., Álvarez-Sánchez, J., de la Paz López, F.,Toledo Moreo, J., Adeli, H. (eds.) From Bioinspired Systems and Biomedical Applications to Machine Learning, IWINAC 2019. LNCS, vol 11487, pp. 452–460. Springer, Cham, (2019). https://doi.org/10.1007/978-3-030-19651_644

  5. Dzanic, T., Shah, K., Witherden, F.: Fourier spectrum discrepancies in deep network generated images, November 2019

    Google Scholar 

  6. Eiter, T., Mannila, H.: Computing discrete Fréchet distance. Tech. rep. (1994)

    Google Scholar 

  7. Goodfellow, I.J., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems (2014). https://doi.org/10.3156/jsoft.29.5_177_2

  8. Guberman, N.: On complex valued convolutional neural networks, February 2016. http://arxiv.org/abs/1602.09046

  9. Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.: Improved training of wasserstein GANs. In: Advances in Neural Information Processing Systems (2017)

    Google Scholar 

  10. Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in Neural Information Processing Systems (2017)

    Google Scholar 

  11. Goodfellow, I., Yoshua Bengio, A.C.: Front Matter. In: Linear Algebra, pp. i–ii. Elsevier (2014). https://doi.org/10.1016/B978-0-12-391420-0.09987-X

  12. Im, D.J., Kim, C.D., Jiang, H., Memisevic, R.: Generating images with recurrent adversarial networks, February 2016

    Google Scholar 

  13. Isensee, F., et al.: Automated brain extraction of multisequence MRI using artificial neural networks. Hum. Brain Mapp. (2019). https://doi.org/10.1002/hbm.24750

    Article  Google Scholar 

  14. Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR, pp. 4396–4405. IEEE, June 2019, https://doi.org/10.1109/CVPR.2019.00453

  15. Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of StyleGAN. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR, pp. 8107–8116. IEEE, June 2020. https://doi.org/10.1109/CVPR42600.2020.00813

  16. Olsson, C., Bhupatiraju, S., Brown, T., Odena, A., Goodfellow, I.: Skill rating for generative models, August 2018. http://arxiv.org/abs/1808.04888

  17. Raghu, M., Zhang, C., Kleinberg, J., Bengio, S.: Transfusion: understanding transfer learning for medical imaging. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems. Curran Associates Inc. (2019). https://papers.nips.cc/paper/2019/hash/eb1e78328c46506b46a4ac4a1e378b91-Abstract.html

  18. Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: Advances in Neural Information Processing Systems (2016)

    Google Scholar 

  19. Shmelkov, K., Schmid, C., Alahari, K.: How good is my GAN? pp. 218–234, July 2018. https://doi.org/10.1007/978-3-030-01216-8_14

  20. Tygert, M., Bruna, J., Chintala, S., LeCun, Y., Piantino, S., Szlam, A.: A mathematical motivation for complex-valued convolutional networks. Neural Comput. 28(5), 815–825 (2016). https://doi.org/10.1162/NECO_a_00824, https://direct.mit.edu/neco/article/28/5/815-825/8157

  21. Veeling, B.S., Linmans, J., Winkens, J., Cohen, T., Welling, M.: Rotation equivariant CNNS for digital pathology. In: Frangi, A., Schnabel, J., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) Medical Image Computing and Computer Assisted Intervention–MICCAI 2018. LNCS, vol. 11071, pp. 210–218. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00934-2_24

  22. Wang, S.Y., Wang, O., Zhang, R., Owens, A., Efros, A.A.: CNN-Generated images are surprisingly easy to spot... for now. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR, pp. 8692–8701. IEEE, June 2020. https://doi.org/10.1109/CVPR42600.2020.00872

  23. Worrall, D.E., Garbin, S.J., Turmukhambetov, D., Brostow, G.J.: Harmonic networks: deep translation and rotation equivariance. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 7168–7177. IEEE, July 2017. https://doi.org/10.1109/CVPR.2017.758

  24. Yazıcı, Y., Foo, C.S., Winkler, S., Yap, K.H., Piliouras, G., Chandrasekhar, V.: The unusual effectiveness of averaging in GAN training. In: 7th International Conference on Learning Representations, ICLR 2019, June 2018

    Google Scholar 

  25. Zhang, X., Karaman, S., Chang, S.F.: Detecting and simulating artifacts in GAN fake images. In: 2019 IEEE International Workshop on Information Forensics and Security, WIFS, pp. 1–6. IEEE, December 2019. https://doi.org/10.1109/WIFS47025.2019.9035107

Download references

Acknowledgments

The authors gratefully acknowledge research project PID2019-110686RB-I00 of the State Research Program Oriented to the Challenges of Society.

Author information

Authors and Affiliations

  1. Artificial Intelligence Department, UNED, Madrid, Spain

    J. Gamazo, J. M. Cuadra & M. Rincón

Authors
  1. J. Gamazo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. J. M. Cuadra
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. M. Rincón
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to M. Rincón .

Editor information

Editors and Affiliations

  1. Universidad Politécnica de Cartagena, Cartagena, Spain

    José Manuel Ferrández Vicente

  2. Universidad Nacional de Educación a Distancia, Madrid, Spain

    José Ramón Álvarez-Sánchez

  3. Universidad Nacional de Educación a Distancia, Madrid, Spain

    Félix de la Paz López

  4. Ohio State University, Columbus, OH, USA

    Hojjat Adeli

Rights and permissions

Reprints and permissions

Copyright information

© 2022 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Gamazo, J., Cuadra, J.M., Rincón, M. (2022). An Efficient and Rotation Invariant Fourier-Based Metric for Assessing the Quality of Images Created by Generative Models. In: Ferrández Vicente, J.M., Álvarez-Sánchez, J.R., de la Paz López, F., Adeli, H. (eds) Bio-inspired Systems and Applications: from Robotics to Ambient Intelligence. IWINAC 2022. Lecture Notes in Computer Science, vol 13259. Springer, Cham. https://doi.org/10.1007/978-3-031-06527-9_41

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-06527-9_41

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-06526-2

  • Online ISBN: 978-3-031-06527-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation