• Corpus ID: 232014582

Uncertainty-aware Generalized Adaptive CycleGAN

@article{Upadhyay2021UncertaintyawareGA,
  title={Uncertainty-aware Generalized Adaptive CycleGAN},
  author={Uddeshya Upadhyay and Yanbei Chen and Zeynep Akata},
  journal={ArXiv},
  year={2021},
  volume={abs/2102.11747}
}
Unpaired image-to-image translation refers to learning inter-image-domain mapping in an unsupervised manner. Existing methods often learn deterministic mappings without explicitly modelling the robustness to outliers or predictive uncertainty, leading to performance degradation when encountering unseen out-of-distribution (OOD) patterns at test time. To address this limitation, we propose a novel probabilistic method called Uncertaintyaware Generalized Adaptive Cycle Consistency (UGAC), which… 

Figures and Tables from this paper

Uncertainty-Guided Progressive GANs for Medical Image Translation
TLDR
This work proposes an uncertainty-guided progressive learning scheme for image-to-image translation by incorporating aleatoric uncertainty as attention maps for GANs trained in a progressive manner, which improves performance over state of the art under fullsupervision and weak-supervision with limited data.

References

SHOWING 1-10 OF 48 REFERENCES
Contrastive Learning for Unpaired Image-to-Image Translation
TLDR
The framework enables one-sided translation in the unpaired image-to-image translation setting, while improving quality and reducing training time, and can be extended to the training setting where each "domain" is only a single image.
Unsupervised Image-to-Image Translation Networks
TLDR
This work makes a shared-latent space assumption and proposes an unsupervised image-to-image translation framework based on Coupled GANs that achieves state-of-the-art performance on benchmark datasets.
Adversarial Self-Defense for Cycle-Consistent GANs
TLDR
Making the translation model more robust to the self-adversarial attack increases its generation quality and reconstruction reliability and makes the model less sensitive to low-amplitude perturbations.
Image Synthesis in Multi-Contrast MRI With Conditional Generative Adversarial Networks
TLDR
The proposed approach preserves intermediate-to-high frequency details via an adversarial loss, and it offers enhanced synthesis performance via pixel-wise and perceptual losses for registered multi-contrast images and a cycle-consistency loss for unregistered images.
Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks
TLDR
Experiments with segmentation of fetal brains and brain tumors from 2D and 3D Magnetic Resonance Images showed that the test-time augmentation-based aleatoric uncertainty provides a better uncertainty estimation than calculating theTest-time dropout-based model uncertainty alone and helps to reduce overconfident incorrect predictions.
Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping
TLDR
A geometry-consistent generative adversarial network (Gc-GAN) is developed, which enables one-sided unsupervised domain mapping and reduces the space of possible solutions while keep the correct solutions in the search space.
Cross-Domain Synthesis of Medical Images Using Efficient Location-Sensitive Deep Network
TLDR
A novel architecture called location-sensitive deep network LSDN is proposed for synthesizing images across domains that integrates intensity feature from image voxels and spatial information in a principled manner and is computationally efficient, e.g. 26× faster than other sparse representation based methods.
Image-to-Image Translation with Conditional Adversarial Networks
TLDR
Conditional adversarial networks are investigated as a general-purpose solution to image-to-image translation problems and it is demonstrated that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks.
MRI Cross-Modality Image-to-Image Translation
TLDR
A cross-modality generation framework that learns to generate translated modalities from given modalities in MR images by means of a deep learning model that leverages conditional generative adversarial networks (cGANs).
MedGAN: Medical Image Translation using GANs
TLDR
A new framework, named MedGAN, is proposed for medical image-to-image translation which operates on the image level in an end- to-end manner and outperforms other existing translation approaches.
...
1
2
3
4
5
...