BoxMask: Revisiting Bounding Box Supervision for Video Object Detection

BoxMask: Revisiting Bounding Box Supervision for Video Object Detection
Khurram Azeem Hashmi, Alain Pagani, Didier Stricker, Muhammad Zeshan Afzal
Winter Conference on Applications of Computer Vision 2023. IEEE Winter Conference on Applications of Computer Vision (WACV-2023) IEEE Winter Conference on Applications of Computer Vision (WACV-2023) befindet sich WACV January 3-8 Waikoloa, Hawaii HI United States CVF 2023 .

Abstract:: We present a new, simple yet effective approach to uplift video object detection. We observe that prior works operate on instance-level feature aggregation that imminently neglects the refined pixel-level representation, resulting in confusion among objects sharing similar appearance or motion characteristics. To address this limitation, we propose BoxMask, which effectively learns discriminative representations by incorporating class-aware pixel-level information. We simply consider bounding box-level annotations as a coarse mask for each object to supervise our method. The proposed module can be effortlessly integrated into any region-based detector to boost detection. Extensive experiments on ImageNet VID and EPIC KITCHENS datasets demonstrate consistent and significant improvement when we plug our BoxMask module into numerous recent state-of-the-art methods.

Back to the overview

Link 1

Link 2