Edge Wasserstein Distance Loss for Oriented Object Detection

Yuke Zhu, Yumeng Ruan, Zihua Xiong, Yue Zhang, Feng Wei, Bing Han, Sheng Guo

Keywords: oriented object detection, regression loss design

TL;DR: This paper proposes a novel orinted object regression loss

Abstract: Regression loss design is an essential topic for oriented object detection. Due to the periodicity of the angle and the ambiguity of width and height definition, traditional L1-distance losses and its variants have been suffered from the metric discontinuity and the square-like problem. As a solution, the distribution based methods show significant advantage by representing oriented boxes as distributions. Differing from exploited the Gaussian distribution to get analytical form of distance measure, we propose a novel oriented regression loss, Wasserstein Distance(EWD) loss, to alleviate the square-like problem.Specifically, for the oriented box representation, we choose a specially-designed distribution whose probability density function is only nonzero over the edges. On this basis, we develop Wasserstein distance as the measure. Besides, based on the edge representation of oriented box, the EWD loss can be generalized to quadrilateral and polynomial regression scenery. Experiments on multiple popular datasets and different detectors show the effectiveness of the proposed method.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning