Litcius/Paper detail

AFWS: Angle-Free Weakly Supervised Rotating Object Detection for Remote Sensing Images

Junyan Lu, Qinglei Hu, Ruifei Zhu, Yali Wei, Tie Li

2024IEEE Transactions on Geoscience and Remote Sensing12 citationsDOI

Abstract

Horizontal annotation-based weakly supervised rotating object detection is a research field that has just been explored. This concept is expected to have a transformative effect on the advancement of data-driven rotating object detection methods. Existing pioneering researches directly regress the rotating rectangle based on angle description, which mainly face two limitations under the weakly supervised framework: 1) the regression form of weakly supervised learning is redundant relative to the training objective, thereby increasing the difficulty of model training and 2) the training objective of self-supervised (SS) learning does not have a close logical relationship with the test metrics, which may result in loss of accuracy. Addressing the above issues, this article proposes an angle-free weakly supervised rotating object detection framework, whose salient points mainly include the following: 1) by improving an angle-free rotating object representation, the decoupling between horizontal and rotating regression parameters in describing rotating objects is achieved; 2) a weakly supervised learning pipeline that is completely equivalent to the common horizontal object detection is designed to effectively relieve the difficulty of model training; and 3) a geometrically intuitive SS learning loss function is introduced to bridge the gap between the training objective and testing metrics. Experimental results on multiple large-scale remote sensing datasets confirm that the accuracy of this method is superior to the state-of-the-art (SOTA) weakly supervised rotating object detection methods, and is competitive even with SOTA fully supervised-related works.

Topics & Concepts

Remote sensingComputer visionObject detectionArtificial intelligenceComputer scienceObject (grammar)GeologyPattern recognition (psychology)Remote-Sensing Image ClassificationAdvanced Image and Video Retrieval TechniquesSatellite Image Processing and Photogrammetry