English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Arbitrary-oriented objects exist widely in natural scenes, and thus theoriented object detection has received extensive attention in recent years. Themainstream rotation detectors use oriented bounding boxes (OBB) orquadrilateral bounding boxes (QBB) to represent the rotating objects. However,these methods suffer from the representation ambiguity for oriented objectdefinition, which leads to suboptimal regression optimization and theinconsistency between the loss metric and the localization accuracy of thepredictions. In this paper, we propose a Representation Invariance Loss (RIL)to optimize the bounding box regression for the rotating objects. Specifically,RIL treats multiple representations of an oriented object as multipleequivalent local minima, and hence transforms bounding box regression into anadaptive matching process with these local minima. Then, the Hungarian matchingalgorithm is adopted to obtain the optimal regression strategy. We also proposea normalized rotation loss to alleviate the weak correlation between differentvariables and their unbalanced loss contribution in OBB representation.Extensive experiments on remote sensing datasets and scene text datasets showthat our method achieves consistent and substantial improvement. The sourcecode and trained models are available at https://github.com/ming71/RIDet.

Optimization for Arbitrary-Oriented Object Detection via Representation Invariance Loss