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

Weiping Yu, Taojiannan Yang, Chen Chen; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2021, pp. 3258-3267

Abstract


Existing methods for object detection in UAV images ignored an important challenge -- imbalanced class distribution -- which leads to poor performance on tail classes. We systematically investigate existing solutions to long-tail problems and unveil that re-balancing methods that are effective on natural image datasets cannot be trivially applied to UAV datasets. To this end, we rethink long-tailed object detection in UAV images and propose the Dual Sampler and Head detection Network (DSHNet), which is the first work that aims to resolve long-tail distribution in UAV images. The key components in DSHNet include Class-Biased Samplers (CBS) and Bilateral Box Heads (BBH), which are developed to cope with tail classes and head classes in a dual-path manner. Without bells and whistles, DSHNet significantly boosts the performance of tail classes on different detection frameworks. Moreover, DSHNet significantly outperforms base detectors and generic approaches for long-tail problems on VisDrone and UAVDT datasets. It achieves a new state-of-the-art performance when combining with image cropping methods.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Yu_2021_WACV, author = {Yu, Weiping and Yang, Taojiannan and Chen, Chen}, title = {Towards Resolving the Challenge of Long-Tail Distribution in UAV Images for Object Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2021}, pages = {3258-3267} }