CVNov 11, 2020

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

arXiv:2011.05523v214 citationsHas Code
AI Analysis

This work addresses the challenge of accurate object detection in low-light conditions for applications like autonomous driving, but it is incremental as it builds on existing loss function methods.

The paper tackles the problem of improving object detection precision by optimizing both classification and localization loss functions, specifically for nighttime vehicle detection, and reports outstanding performance improvements on two datasets.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes