RADA: Robust Adversarial Data Augmentation for Camera Localization in Challenging Weather
This addresses robustness issues in camera localization for robotics, offering a domain-specific improvement over existing augmentation techniques.
The paper tackles the problem of camera localization robustness under domain shifts like weather changes by proposing RADA, a data augmentation method that perturbs geometrically informative image parts, resulting in up to two times higher accuracy than state-of-the-art models in unseen challenging conditions.
Camera localization is a fundamental and crucial problem for many robotic applications. In recent years, using deep-learning for camera-based localization has become a popular research direction. However, they lack robustness to large domain shifts, which can be caused by seasonal or illumination changes between training and testing data sets. Data augmentation is an attractive approach to tackle this problem, as it does not require additional data to be provided. However, existing augmentation methods blindly perturb all pixels and therefore cannot achieve satisfactory performance. To overcome this issue, we proposed RADA, a system whose aim is to concentrate on perturbing the geometrically informative parts of the image. As a result, it learns to generate minimal image perturbations that are still capable of perplexing the network. We show that when these examples are utilized as augmentation, it greatly improves robustness. We show that our method outperforms previous augmentation techniques and achieves up to two times higher accuracy than the SOTA localization models (e.g., AtLoc and MapNet) when tested on `unseen' challenging weather conditions.