Litcius/Paper detail

You Get What You Focus on: A Weighting Factor for IoU-based Regression Loss

Xinyu Gu, Chao Gao, Zheng Lu, Tianxiang Cui

202110 citationsDOI

Abstract

Loss functions are essential to bounding box regression which plays a significant role in deep learning based object detection. Despite the effectiveness of the popular Intersection over Union (IoU) based losses, there is still an imbalance problem of high- and low-quality predicted bounding boxes, impeding the accuracy and convergence speed during bound box regression. Specifically, we observe that the huge amount of predicted bounding boxes having small overlapping regions with ground truth box overwhelms the amount of predicted bounding boxes having large overlapping regions. In this paper, we propose a simple weighting factor that is able to reshape the existing IoU-based losses according to a geometric relationship of bounding boxes. In this way, we are able to effectively down-weight the contribution of low-quality predicted boxes and focus training on high-quality ones. Extensive experiments have been carried out on popular IoU-based losses with various object detection techniques. By simply incorporating the proposed weighting factor, we are able to achieve notable performance gains on the popular MS COCO dataset.

Topics & Concepts

Bounding overwatchWeightingComputer scienceMinimum bounding boxFocus (optics)Intersection (aeronautics)Convergence (economics)RegressionArtificial intelligenceObject (grammar)Object detectionGround truthA-weightingQuality (philosophy)Upper and lower boundsPattern recognition (psychology)AlgorithmData miningMathematicsStatisticsEngineeringImage (mathematics)EconomicsPhysicsMathematical analysisMedicineRadiologyPhilosophyAerospace engineeringEconomic growthOpticsEpistemologyAdvanced Neural Network ApplicationsDomain Adaptation and Few-Shot LearningAdversarial Robustness in Machine Learning
You Get What You Focus on: A Weighting Factor for IoU-based Regression Loss | Litcius