Timezone: »

 
Spotlight
Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss
Xue Yang · Junchi Yan · Qi Ming · Wentao Wang · xiaopeng zhang · Qi Tian

Tue Jul 20 06:25 PM -- 06:30 PM (PDT) @

Boundary discontinuity and its inconsistency to the final detection metric have been the bottleneck for rotating detection regression loss design. In this paper, we propose a novel regression loss based on Gaussian Wasserstein distance as a fundamental approach to solve the problem. Specifically, the rotated bounding box is converted to a 2-D Gaussian distribution, which enables to approximate the indifferentiable rotational IoU induced loss by the Gaussian Wasserstein distance (GWD) which can be learned efficiently by gradient back-propagation. GWD can still be informative for learning even there is no overlapping between two rotating bounding boxes which is often the case for small object detection. Thanks to its three unique properties, GWD can also elegantly solve the boundary discontinuity and square-like problem regardless how the bounding box is defined. Experiments on five datasets using different detectors show the effectiveness of our approach, and codes are available at https://github.com/yangxue0827/RotationDetection.

Author Information

Xue Yang (Shanghai Jiao Tong University)

Xue Yang is now a Ph.D. student in Wu Honor Class, Department of Computer Science and Engineering, Shanghai Jiao Tong University starting from Autumn 2019. His research advisor is Prof. Junchi Yan. Xue Yang received the B. E. degree from School of Information Science and Engineering, Central South University, Hunan, China, in 2016. He received the M. S. degree from School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China, in 2019.

Junchi Yan (Shanghai Jiao Tong University)
Qi Ming (School of Automation, Beijing Institute of Technology)
Wentao Wang (Shanghai Jiao Tong University)
xiaopeng zhang (Huawei Cloud EI )
Qi Tian (Huawei Cloud & AI)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors