Restyling Data: Application to Unsupervised Domain Adaptation
arXiv:1909.10900
Abstract
Machine learning is driven by data, yet while their availability is constantly increasing, training data require laborious, time consuming and error-prone labelling or ground truth acquisition, which in some cases is very difficult or even impossible. Recent works have resorted to synthetic data generation, but the inferior performance of models trained on synthetic data when applied to the real world, introduced the challenge of unsupervised domain adaptation. In this work we investigate an unsupervised domain adaptation technique that descends from another perspective, in order to avoid the complexity of adversarial training and cycle consistencies. We exploit the recent advances in photorealistic style transfer and take a fully data driven approach. While this concept is already implicitly formulated within the intricate objectives of domain adaptation GANs, we take an explicit approach and apply it directly as data pre-processing. The resulting technique is scalable, efficient and easy to implement, offers competitive performance to the complex state-of-the-art alternatives and can open up new pathways for domain adaptation.
References in corpus (9)
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
- Joint 2D-3D-Semantic Data for Indoor Scene Understanding
- Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
- Matterport3D: Learning from RGB-D Data in Indoor Environments
- Virtual Worlds as Proxy for Multi-Object Tracking Analysis
- Style Augmentation: Data Augmentation via Style Randomization
- A Kernel Theory of Modern Data Augmentation
- Semantic-aware Grad-GAN for Virtual-to-Real Urban Scene Adaption