Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss

by   Xue Yang, et al.

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. Codes are available at


page 1

page 4


Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression

Bounding box regression is the crucial step in object detection. In exis...

MKIoU Loss: Towards Accurate Oriented Object Detection in Aerial Images

Oriented bounding box regression is crucial for oriented object detectio...

G-Rep: Gaussian Representation for Arbitrary-Oriented Object Detection

Arbitrary-oriented object representations contain the oriented bounding ...

The KFIoU Loss for Rotated Object Detection

Differing from the well-developed horizontal object detection area where...

Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence

Existing rotated object detectors are mostly inherited from the horizont...

Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression

Bounding box (bbox) regression is a fundamental task in computer vision....

A Boundary Regressing Model for Nested Named Entity Recognition

Recognizing named entities (NEs) is commonly conducted as a classificati...