Application of an Improved Focal Loss in Vehicle Detection

Date
2020
Authors
He, X
Yang, J
Kasabov, N
Supervisor
Item type
Conference Contribution
Degree name
Journal Title
Journal ISSN
Volume Title
Publisher
Springer
Abstract

Object detection is an important and fundamental task in computer vision. Recently, the emergence of deep neural network has made considerable progress in object detection. Deep neural network object detectors can be grouped in two broad categories: the two-stage detector and the one-stage detector. One-stage detectors are faster than two-stage detectors. However, they suffer from a severe foreground-backg-round class imbalance during training that causes a low accuracy performance. RetinaNet is a one-stage detector with a novel loss function named Focal Loss which can reduce the class imbalance effect. Thereby RetinaNet outperforms all the two-stage and one-stage detectors in term of accuracy. The main idea of focal loss is to add a modulating factor to rectify the cross-entropy loss, which down-weights the loss of easy examples during training and thus focuses on the hard examples. However, cross-entropy loss only focuses on the loss of the ground-truth classes and thus it can’t gain the loss feedback from the false classes. Thereby cross-entropy loss does not achieve the best convergence. In this paper, we proposed a new loss function named Dual Cross-Entropy Focal Loss, which improves on the focal loss. Dual cross-entropy focal loss adds a modulating factor to rectify the dual cross-entropy loss towards focusing on the hard samples. Dual cross-entropy loss is an improved variant of cross-entropy loss, which gains the loss feedback from both the ground-truth classes and the false classes. We changed the loss function of RetinaNet from focal loss to our dual cross-entropy focal loss and performed some experiments on a small vehicle dataset. The experimental results show that our new loss function improves the vehicle detection performance.

Description
Keywords
Focal Loss; Class Imbalance; Cross-Entropy Loss; RetinaNet; Vehicle Detection; Object Detection; Deep Neural Network
Source
In: Rutkowski L., Scherer R., Korytkowski M., Pedrycz W., Tadeusiewicz R., Zurada J.M. (eds) Artificial Intelligence and Soft Computing. ICAISC 2020. Lecture Notes in Computer Science, vol 12415. Springer, Cham. https://doi.org/10.1007/978-3-030-61401-0_11
Rights statement
An author may self-archive an author-created version of his/her article on his/her own website and or in his/her institutional repository. He/she may also deposit this version on his/her funder’s or funder’s designated repository at the funder’s request or as a result of a legal obligation, provided it is not made publicly available until 12 months after official publication. He/ she may not use the publisher's PDF version, which is posted on www.springerlink.com, for the purpose of self-archiving or deposit. Furthermore, the author may only post his/her version provided acknowledgement is given to the original source of publication and a link is inserted to the published article on Springer's website. The link must be accompanied by the following text: "The final publication is available at www.springerlink.com”. (Please also see Publisher’s Version and Citation).