Augmented Cyclic Consistency Regularization for Unpaired Image-to-Image Translation

@article{Ohkawa2021AugmentedCC,
  title={Augmented Cyclic Consistency Regularization for Unpaired Image-to-Image Translation},
  author={Takehiko Ohkawa and Naoto Inoue and Hirokatsu Kataoka and Nakamasa Inoue},
  journal={2020 25th International Conference on Pattern Recognition (ICPR)},
  year={2021},
  pages={362-369}
}
Unpaired image-to-image (I2I) translation has received considerable attention in pattern recognition and computer vision because of recent advancements in generative adversarial networks (GANs). However, due to the lack of explicit supervision, unpaired I2I models often fail to generate realistic images, especially in challenging datasets with different backgrounds and poses. Hence, stabilization is indispensable for GANs and applications of I2I translation. Herein, we propose Augmented Cyclic… Expand
1 Citations
Regularization And Normalization For Generative Adversarial Networks: A Review
  • 1
  • PDF

References

SHOWING 1-10 OF 56 REFERENCES
Consistency Regularization for Generative Adversarial Networks
  • 66
  • Highly Influential
  • PDF
Conditional Generative Adversarial Network for Structured Domain Adaptation
  • 152
  • PDF
CyCADA: Cycle-Consistent Adversarial Domain Adaptation
  • 1,185
  • Highly Influential
  • PDF
Image-to-Image Translation with Conditional Adversarial Networks
  • 8,081
  • Highly Influential
  • PDF
Stabilizing Training of Generative Adversarial Networks through Regularization
  • 274
  • PDF
U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
  • 91
  • PDF
A Large-Scale Study on Regularization and Normalization in GANs
  • 71
  • PDF
Unsupervised Image-to-Image Translation Networks
  • 1,379
  • PDF
Image to Image Translation for Domain Adaptation
  • 250
  • PDF
Improved Training of Wasserstein GANs
  • 4,216
  • Highly Influential
  • PDF
...
1
2
3
4
5
...