Optimized Loss Functions for Object detection: A Case Study on Nighttime Vehicle Detection
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 (1)
Tasks
ClassificationGeneral Classificationobject-detectionObject Detectionvehicle detectionSimilar Papers 제목 키워드 기반
MPDIoU: A Loss for Efficient and Accurate Bounding Box Regression
Bounding box regression (BBR) has been widely used in object detection and instance segmentation, which is an important step in object localization. However, most of the existing loss functions for bounding box regressio…
Instance SegmentationObjectobject-detectionObject Detection+4Optimized Hybrid Focal Margin Loss for Crack Segmentation
Many loss functions have been derived from cross-entropy loss functions such as large-margin softmax loss and focal loss. The large-margin softmax loss makes the classification more rigorous and prevents overfitting. The…
Crack SegmentationImage Segmentationobject-detectionObject Detection+2A survey of loss functions for semantic segmentation
Image Segmentation has been an active field of research as it has a wide range of applications, ranging from automated disease detection to self-driving cars. In the past five years, various papers came up with different…
Image SegmentationSegmentationSelf-Driving CarsSemantic Segmentation+2Long-tailed Instance Segmentation using Gumbel Optimized Loss
Major advancements have been made in the field of object detection and segmentation recently. However, when it comes to rare categories, the state-of-the-art methods fail to detect them, resulting in a significant perfor…
Instance Segmentationobject-detectionObject DetectionSegmentationComparing Objective Functions for Segmentation and Detection of Microaneurysms in Retinal Images
Retinal microaneurysms (MAs) are the earliest signs of diabetic retinopathy (DR) which is the leading cause of blindness among the working aged population in the western world. Detection of MAs present a particular chall…