mlsanityData to 14 Oct 2026

Signature and Log-signature for the Study of Empirical Distributions Generated with GANs

arXiv 2203.03226 ↗First posted 7 Mar 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we bring forward the use of the recently developed Signature Transform as a way to measure the similarity between image distributions and provide detailed acquaintance and extensive evaluations. We are the first to pioneer RMSE and MAE Signature, along with log-signature as an alternative to measure GAN convergence, a problem that has been extensively studied. We are also forerunners to introduce analytical measures based on statistics to study the goodness of fit of the GAN sample distribution that are both efficient and effective. Current GAN measures involve lots of computation normally done at the GPU and are very time consuming. In contrast, we diminish the computation time to the order of seconds and computation is done at the CPU achieving the same level of goodness. Lastly, a PCA adaptive t-SNE approach, which is novel in this context, is also proposed for data visualization.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 46 of its 65 references that are in the map. First posted on arXiv 7 Mar 2022.

Builds on

46 of 65 references.

References · 46

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2017Mask R-CNNcited by 7,277
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  6. 2022Generative Adversarial Networkscited by 5,627
  7. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  8. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  9. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  10. 2013Auto-Encoding Variational Bayescited by 4,053
  11. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  12. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
34 more
  1. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  2. 2016Improved Techniques for Training GANscited by 2,970
  3. 2015Fast R-CNNcited by 2,933
  4. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  5. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  6. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  7. 2020Training Generative Adversarial Networks with Limited Datacited by 1,186
  8. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  9. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,098
  10. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,069
  11. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,043
  12. 2018Image Transformercited by 772
  13. 2018Which Training Methods for GANs do actually Converge?cited by 679
  14. 2020Contrastive Learning for Unpaired Image-to-Image Translationcited by 639
  15. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 565
  16. 2018Video-to-Video Synthesiscited by 390
  17. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  18. 2017Data Augmentation Generative Adversarial Networkscited by 278
  19. 2018The relativistic discriminator: a key element missing from standard GANcited by 238
  20. 2017Photographic Image Synthesis with Cascaded Refinement Networkscited by 223
  21. 2016Generating Images with Perceptual Similarity Metrics based on Deep Networkscited by 222
  22. 2017The Numerics of GANscited by 105
  23. 2016A Primer on the Signature Method in Machine Learningcited by 104
  24. 2020Adversarial score matching and improved sampling for image generationcited by 96
  25. 2016Kernels for sequentially ordered datacited by 84
  26. 2019Deep Signature Transformscited by 75
  27. 2021Improved Transformer for High-Resolution GANscited by 59
  28. 2018Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effectcited by 49
  29. 2020Signatory: differentiable computations of the signature and logsignature transforms, on both CPU and GPUcited by 46
  30. 2017Variational Walkback: Learning a Transition Operator as a Stochastic Recurrent Netcited by 30
  31. 2016Preserving Color in Neural Artistic Style Transfercited by 20
  32. 2013Sparse arrays of signatures for online character recognitioncited by 18
  33. 2019Learning stochastic differential equations using RNN with log signature featurescited by 13
  34. 2020Decentralized Visual-Inertial-UWB Fusion for Relative State Estimation of Aerial Swarmcited by 4

Built on by

Not cited yet.