Cycle-Consistent Adversarial Learning as Approximate Bayesian Inference
We formalize the problem of learning interdomain correspondences in the absence of paired data as Bayesian inference in a latent variable model (LVM), where one seeks the underlying hidden representations of entities from one domain as entities from the other domain. First, we introduce implicit latent variable models, where the prior over hidden representations can be specified flexibly as an implicit distribution. Next, we develop a new variational inference (VI) algorithm for this model based on minimization of the symmetric Kullback-Leibler (KL) divergence between a variational joint and the exact joint distribution. Lastly, we demonstrate that the state-of-the-art cycle-consistent adversarial learning (CYCLEGAN) models can be derived as a special case within our proposed VI framework, thus establishing its connection to approximate Bayesian inference methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Bayesian InferenceVariational InferenceSimilar Papers 제목 키워드 기반
Bayesian Cycle-Consistent Generative Adversarial Networks via Marginalizing Latent Sampling
Recent techniques built on Generative Adversarial Networks (GANs), such as Cycle-Consistent GANs, are able to learn mappings among different domains built from unpaired datasets, through min-max optimization games betwee…
Image-to-Image TranslationSemantic SegmentationStyle TransferGradient-Free Adversarial Attacks for Bayesian Neural Networks
The existence of adversarial examples underscores the importance of understanding the robustness of machine learning models. Bayesian neural networks (BNNs), due to their calibrated uncertainty, have been shown to posses…
Adversarial RobustnessBayesian InferenceBayesian Adversarial Spheres: Bayesian Inference and Adversarial Examples in a Noiseless Setting
Modern deep neural network models suffer from adversarial examples, i.e. confidently misclassified points in the input space. It has been shown that Bayesian neural networks are a promising approach for detecting adversa…
Bayesian InferencePCT-CycleGAN: Paired Complementary Temporal Cycle-Consistent Adversarial Networks for Radar-Based Precipitation Nowcasting
The precipitation nowcasting methods have been elaborated over the centuries because rain has a crucial impact on human life. Not only quantitative precipitation forecast (QPF) models and convolutional long short-term me…
Image-to-Image TranslationTime Series AnalysisCycle-Consistent Adversarial GAN: the integration of adversarial attack and defense
In image classification of deep learning, adversarial examples where inputs intended to add small magnitude perturbations may mislead deep neural networks (DNNs) to incorrect results, which means DNNs are vulnerable to t…
Adversarial Attackimage-classificationImage Classification