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

Existing methods for object detection in UAV images ignored an importantchallenge - imbalanced class distribution in UAV images - which leads to poorperformance on tail classes. We systematically investigate existing solutionsto long-tail problems and unveil that re-balancing methods that are effectiveon natural image datasets cannot be trivially applied to UAV datasets. To thisend, we rethink long-tailed object detection in UAV images and propose the DualSampler and Head detection Network (DSHNet), which is the first work that aimsto resolve long-tail distribution in UAV images. The key components in DSHNetinclude Class-Biased Samplers (CBS) and Bilateral Box Heads (BBH), which aredeveloped to cope with tail classes and head classes in a dual-path manner.Without bells and whistles, DSHNet significantly boosts the performance of tailclasses on different detection frameworks. Moreover, DSHNet significantlyoutperforms base detectors and generic approaches for long-tail problems onVisDrone and UAVDT datasets. It achieves new state-of-the-art performance whencombining with image cropping methods. Code is available athttps://github.com/we1pingyu/DSHNet

Towards Resolving the Challenge of Long-tail Distribution in UAV Images for Object Detection