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

Deep Neural Networks (DNNs) are a critical component for self-drivingvehicles. They achieve impressive performance by reaping information from highamounts of labeled data. Yet, the full complexity of the real world cannot beencapsulated in the training data, no matter how big the dataset, and DNNs canhardly generalize to unseen conditions. Robustness to various imagecorruptions, caused by changing weather conditions or sensor degradation andaging, is crucial for safety when such vehicles are deployed in the real world.We address this problem through a novel type of layer, dubbed StyleLess, whichenables DNNs to learn robust and informative features that can cope withvarying external conditions. We propose multiple variations of this layer thatcan be integrated in most of the architectures and trained jointly with themain task. We validate our contribution on typical autonomous-driving tasks(detection, semantic segmentation), showing that in most cases, this approachimproves predictive performance on unseen conditions (fog, rain), whilepreserving performance on seen conditions and objects.

StyleLess layer: Improving robustness for real-world driving