Abstract
With the increase of road mileage, the complexity of road conditions and the increasing demand for real-time update of road data, more accurate and efficient road detection methods are gradually put on the agenda. Among them, the road detection method based on deep learning has the greatest potential at present. In order to improve the efficiency of the neural network, this paper introduces the definition of the loss function, the main classification of the loss function, the advantages and disadvantages of the corresponding and the application of the loss function from the perspective of the loss function.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Liu, R.: Research and Improvement of High Resolution Remote Sensing Image Road Extraction Algorithm. Xidian University (2019)
Hong, Z.: Road extraction from high spatial resolution remote sensing images based on deconvolution network. China University of Geosciences, Beijing
Deng, J., Zhang, S., Zhang, J., et al.: Research on loss function and its application in supervised learning. Big Data 000(001), 60–80 (2020)
Li, X., Wu, L.: Reliability model with risk dependent effect under MLINEX loss function. J. Jiangxi Norm. Univ. Nat. Sci. Edn. 1, 17–19 (2020)
Sun, M., Zhang, X.: Study on tongue image classification method based on loss function of TripleLoss. Beijing Biomed. Eng. 39(02), 25–31 (2020)
Shannon, C.E.: A mathematical theory of communication. Bell Syst. Tech. J. 27(3), 379–423 (1948)
Mitchell, T.M., Carbonell, J.G., Michalski, R.S.: Machine Learning. China Machine Press (2003)
Liu, W., Pokharel, P.P., Principe, J.C.: Correntropy: properties and applications in non-
Gaussian signal processing. IEEE Trans. Signal Process. 55(11), 5286–5297 (2007)
Guo, Y., Alimujiang, A., Nurbiya, Y., Zhu, Y., Kuerban, W.: Multi-country face classification and recognition based on MobileNet network. Image Signal Process. 9(3), 146–155 (2020)
Rezatofighi, H., Tsoi, N., Gwak, J.Y., et al.: Generalized intersection over union: a metric and a loss for bounding box regression (2019)
Generalized intersection over union: a metric and a loss for bounding box regression (2019)
Rezatofighi, H., Tsoi, N., Gwak, J.Y., Sadeghian, A., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2019)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Du, H. (2021). Comparative Study of Loss Function Based on Neural Network. In: Cao, W., Ozcan, A., Xie, H., Guan, B. (eds) Computing and Data Science. CONF-CDS 2021. Communications in Computer and Information Science, vol 1513. Springer, Singapore. https://doi.org/10.1007/978-981-16-8885-0_26
Download citation
DOI: https://doi.org/10.1007/978-981-16-8885-0_26
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-8884-3
Online ISBN: 978-981-16-8885-0
eBook Packages: Computer ScienceComputer Science (R0)