Optimized Loss Functions for Object detection: A Case Study on Nighttime Vehicle Detection

TL;DR

This paper introduces optimized loss functions for object detection that improve nighttime vehicle detection accuracy by establishing correlation between classification and localization, and proposing a novel MIoU loss to enhance localization precision.

Contribution

The paper proposes a new correlation-based classification loss and a MIoU localization loss, addressing gradient inconsistency and improving detection performance.

Findings

Significant improvement in nighttime vehicle detection accuracy

Effective correlation between classification and localization tasks

Proposed MIoU loss eliminates gradient inconsistency

Abstract

Loss functions is a crucial factor that affecting the detection precision in object detection task. In this paper, we optimize both two loss functions for classification and localization simultaneously. Firstly, by multiplying an IoU-based coefficient by the standard cross entropy loss in classification loss function, the correlation between localization and classification is established. Compared to the existing studies, in which the correlation is only applied to improve the localization accuracy for positive samples, this paper utilizes the correlation to obtain the really hard negative samples and aims to decrease the misclassified rate for negative samples. Besides, a novel localization loss named MIoU is proposed by incorporating a Mahalanobis distance between predicted box and target box, which eliminate the gradients inconsistency problem in the DIoU loss, further improving the localization accuracy. Finally, sufficient experiments for nighttime vehicle detection have been done on two datasets. Our results show than when train with the proposed loss functions, the detection performance can be outstandingly improved. The source code and trained models are available at https://github.com/therebellll/NegIoU-PosIoU-Miou.