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

Several popular computer vision (CV) datasets, specifically employed forObject Detection (OD) in autonomous driving tasks exhibit biases due to a rangeof factors including weather and lighting conditions. These biases may impair amodel's generalizability, rendering it ineffective for OD in novel and unseendatasets. Especially, in autonomous driving, it may prove extremely high riskand unsafe for the vehicle and its surroundings. This work focuses onunderstanding these datasets better by identifying such "good-weather" bias.Methods to mitigate such bias which allows the OD models to perform better andimprove the robustness are also demonstrated. A simple yet effective ODframework for studying bias mitigation is proposed. Using this framework, theperformance on popular datasets is analyzed and a significant difference inmodel performance is observed. Additionally, a knowledge transfer technique anda synthetic image corruption technique are proposed to mitigate the identifiedbias. Finally, using the DAWN dataset, the findings are validated on the ODtask, demonstrating the effectiveness of our techniques in mitigatingreal-world "good-weather" bias. The experiments show that the proposedtechniques outperform baseline methods by averaged fourfold improvement.

In Rain or Shine: Understanding and Overcoming Dataset Bias for Improving Robustness Against Weather Corruptions for Autonomous Vehicles