English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Camera localization is a fundamental and crucial problem for many roboticapplications. In recent years, using deep-learning for camera-basedlocalization has become a popular research direction. However, they lackrobustness to large domain shifts, which can be caused by seasonal orillumination changes between training and testing data sets. Data augmentationis an attractive approach to tackle this problem, as it does not requireadditional data to be provided. However, existing augmentation methods blindlyperturb all pixels and therefore cannot achieve satisfactory performance. Toovercome this issue, we proposed RADA, a system whose aim is to concentrate onperturbing the geometrically informative parts of the image. As a result, itlearns to generate minimal image perturbations that are still capable ofperplexing the network. We show that when these examples are utilized asaugmentation, it greatly improves robustness. We show that our methodoutperforms previous augmentation techniques and achieves up to two timeshigher accuracy than the SOTA localization models (e.g., AtLoc and MapNet) whentested on `unseen' challenging weather conditions.

RADA: Robust Adversarial Data Augmentation for Camera Localization in Challenging Weather