Uncertainty-aware Generalized Adaptive CycleGAN
- URL: http://arxiv.org/abs/2102.11747v1
- Date: Tue, 23 Feb 2021 15:22:35 GMT
- Title: Uncertainty-aware Generalized Adaptive CycleGAN
- Authors: Uddeshya Upadhyay, Yanbei Chen, Zeynep Akata
- Abstract summary: 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.
We propose a novel probabilistic method called Uncertainty-aware Generalized Adaptive Cycle Consistency (UGAC)
- Score: 44.34422859532988
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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 Uncertainty-aware Generalized
Adaptive Cycle Consistency (UGAC), which models the per-pixel residual by
generalized Gaussian distribution, capable of modelling heavy-tailed
distributions. We compare our model with a wide variety of state-of-the-art
methods on two challenging tasks: unpaired image denoising in the natural image
and unpaired modality prorogation in medical image domains. Experimental
results demonstrate that our model offers superior image generation quality
compared to recent methods in terms of quantitative metrics such as
signal-to-noise ratio and structural similarity. Our model also exhibits
stronger robustness towards OOD test data.
Related papers
- Confidence-Aware and Self-Supervised Image Anomaly Localisation [7.099105239108548]
We discuss an improved self-supervised single-class training strategy that supports the approximation of probabilistic inference with loosen feature locality constraints.
Our method is integrated into several out-of-distribution (OOD) detection models and we show evidence that our method outperforms the state-of-the-art on various benchmark datasets.
arXiv Detail & Related papers (2023-03-23T12:48:47Z) - Masked Images Are Counterfactual Samples for Robust Fine-tuning [77.82348472169335]
Fine-tuning deep learning models can lead to a trade-off between in-distribution (ID) performance and out-of-distribution (OOD) robustness.
We propose a novel fine-tuning method, which uses masked images as counterfactual samples that help improve the robustness of the fine-tuning model.
arXiv Detail & Related papers (2023-03-06T11:51:28Z) - Deblurring via Stochastic Refinement [85.42730934561101]
We present an alternative framework for blind deblurring based on conditional diffusion models.
Our method is competitive in terms of distortion metrics such as PSNR.
arXiv Detail & Related papers (2021-12-05T04:36:09Z) - Robustness via Uncertainty-aware Cycle Consistency [44.34422859532988]
Unpaired image-to-image translation refers to learning inter-image-domain mapping without corresponding image pairs.
Existing methods learn deterministic mappings without explicitly modelling the robustness to outliers or predictive uncertainty.
We propose a novel probabilistic method based on Uncertainty-aware Generalized Adaptive Cycle Consistency (UGAC)
arXiv Detail & Related papers (2021-10-24T15:33:21Z) - Uncertainty-aware GAN with Adaptive Loss for Robust MRI Image
Enhancement [3.222802562733787]
Conditional generative adversarial networks (GANs) have shown improved performance in learning photo-realistic image-to-image mappings.
This paper proposes a GAN-based framework that (i)models an adaptive loss function for robustness to OOD-noisy data and (ii)estimates the per-voxel uncertainty in the predictions.
We demonstrate our method on two key applications in medical imaging: (i)undersampled magnetic resonance imaging (MRI) reconstruction (ii)MRI modality propagation.
arXiv Detail & Related papers (2021-10-07T11:29:03Z) - Low-Light Image Enhancement with Normalizing Flow [92.52290821418778]
In this paper, we investigate to model this one-to-many relationship via a proposed normalizing flow model.
An invertible network that takes the low-light images/features as the condition and learns to map the distribution of normally exposed images into a Gaussian distribution.
The experimental results on the existing benchmark datasets show our method achieves better quantitative and qualitative results, obtaining better-exposed illumination, less noise and artifact, and richer colors.
arXiv Detail & Related papers (2021-09-13T12:45:08Z) - Understanding the Intrinsic Robustness of Image Distributions using
Conditional Generative Models [87.00072607024026]
We study the intrinsic robustness of two common image benchmarks under $ell$ perturbations.
We show the existence of a large gap between the robustness limits implied by our theory and the adversarial robustness achieved by current state-of-the-art robust models.
arXiv Detail & Related papers (2020-03-01T01:45:04Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.