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

Performance monitoring of object detection is crucial for safety-criticalapplications such as autonomous vehicles that operate under varying and complexenvironmental conditions. Currently, object detectors are evaluated usingsummary metrics based on a single dataset that is assumed to be representativeof all future deployment conditions. In practice, this assumption does nothold, and the performance fluctuates as a function of the deploymentconditions. To address this issue, we propose an introspection approach toperformance monitoring during deployment without the need for ground truthdata. We do so by predicting when the per-frame mean average precision dropsbelow a critical threshold using the detector's internal features. Wequantitatively evaluate and demonstrate our method's ability to reduce risk bytrading off making an incorrect decision by raising the alarm and absentingfrom detection.

Per-frame mAP Prediction for Continuous Performance Monitoring of Object Detection During Deployment