Learning to adapt: domain adaptation with cycle-consistent generative adversarial networks
Date
2023
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
University of the Witwatersrand, Johannesburg
Abstract
Domain adaptation is a critical part of modern-day machine learning as many practitioners do not have the means to collect and label all the data they require reliably. Instead, they often turn to large online datasets to meet their data needs. However, this can often lead to a mismatch between the online dataset and the data they will encounter in their own problem. This is known as domain shift and plagues many different avenues of machine learning. From differences in data sources, changes in the underlying processes generating the data, or new unseen environments the models have yet to encounter. All these issues can lead to performance degradation. From the success in using Cycle-consistent Generative Adversarial Networks(CycleGAN) to learn unpaired image-to-image mappings, we propose a new method to help alleviate the issues caused by domain shifts in images. The proposed model incorporates an adversarial loss to encourage realistic-looking images in the target domain, a cycle-consistency loss to learn an unpaired image-to-image mapping, and a semantic loss from a task network to improve the generator’s performance. The task network is con-currently trained with the generators on the generated images to improve downstream task performance on adapted images. By utilizing the power of CycleGAN, we can learn to classify images in the target domain without any target domain labels. In this research, we show that our model is successful on various unsupervised domain adaptation (UDA) datasets and can alleviate domain shifts for different adaptation tasks, like classification or semantic segmentation. In our experiments on standard classification, we were able to bring the models performance to near oracle level accuracy on a variety of different classification datasets. The semantic segmentation experiments showed that our model could improve the performance on the target domain, but there is still room for further improvements. We also further analyze where our model performs well and where improvements can be made.
Description
A dissertation submitted in fulfilment of the degree of Master of Science in Computer Science, to the Faculty of Science, School of Computer Science and Applied Mathematics, University of the Witwatersrand, Johannesburg, 2023.
Keywords
Machine learning, Computer vision, Generative modelling, Generative Adversarial Networks (GAN), Image-to-Image translation, Domain adaptation, Classification, Semantic segmentation, Cycle-Consistent Generative Adversarial Networks, UCTD
Citation
Burke, Pierce William. (2023). Learning to adapt: domain adaptation with cycle-consistent generative adversarial networks. [Master's dissertation, University of the Witwatersrand, Johannesburg]. https://hdl.handle.net/10539/41667