Bayesian Cycle-Consistent Generative Adversarial Networks via Marginalizing Latent Sampling
| Autor: | Yu Cheng, Tianheng Cheng, Haoran You, Chun-Liang Li, Pan Zhou |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer Networks and Communications Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) Bayesian probability Computer Science - Computer Vision and Pattern Recognition Process (computing) Sampling (statistics) Inference Machine Learning (stat.ML) Latent variable Machine learning computer.software_genre Machine Learning (cs.LG) Computer Science Applications ComputingMethodologies_PATTERNRECOGNITION Statistics - Machine Learning Artificial Intelligence Maximum a posteriori estimation Artificial intelligence business computer Software |
| Zdroj: | IEEE Transactions on Neural Networks and Learning Systems. 32:4389-4403 |
| ISSN: | 2162-2388 2162-237X |
| DOI: | 10.1109/tnnls.2020.3017669 |
| Popis: | 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 between generators and discriminators. However, it remains challenging to stabilize the training process and thus cyclic models fall into mode collapse accompanied by the success of discriminator. To address this problem, we propose an novel Bayesian cyclic model and an integrated cyclic framework for inter-domain mappings. The proposed method motivated by Bayesian GAN explores the full posteriors of cyclic model via sampling latent variables and optimizes the model with maximum a posteriori (MAP) estimation. Hence, we name it Bayesian CycleGAN. In addition, original CycleGAN cannot generate diversified results. But it is feasible for Bayesian framework to diversify generated images by replacing restricted latent variables in inference process. We evaluate the proposed Bayesian CycleGAN on multiple benchmark datasets, including Cityscapes, Maps, and Monet2photo. The proposed method improve the per-pixel accuracy by 15% for the Cityscapes semantic segmentation task within origin framework and improve 20% within the proposed integrated framework, showing better resilience to imbalance confrontation. The diversified results of Monet2Photo style transfer also demonstrate its superiority over original cyclic model. We provide codes for all of our experiments in https://github.com/ranery/Bayesian-CycleGAN. Comment: Accepted by IEEE TNNLS |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|