Abstract
The foreground-background class imbalance in target detection is inevitable, which is caused by the training data set. Specifically, the number of targets contained in any image of the training data set is generally very small, that is, the number of positive examples is small, while the number of the negative examples from the background is large. Therefore, the ability of the algorithm to detect the negatives is stronger than that of positive examples. The Focal Loss algorithm solves this problem by improving the classification loss function. However, Focal Loss brings additional hyper-parameters, which remains to be further adjusted. This paper refers to the idea of Focal Loss from the classification loss function, and proposes new a classification loss function SCE that is similar to Focal Loss but does not contain any extra hyper-parameters. Experiments in the paper prove that SCE can obtain performance equivalent to Focal Loss without introducing hyper-parameters.
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
Zou, Z., Shi, Z., Guo, Y., Ye, J.: Object Detection in 20 Years: A Survey. arXiv Prepr arXiv:1905.05055v2 (2019)
Wu, X., Sahoo, D., Hoi, S.: Recent advances in deep learning for object detection. Neurocomputing 396, 39–64 (2020). https://doi.org/10.1016/j.neucom.2020.01.085
Hariharan, B., Arbeláez, P., Girshick, R., Malik, J.: Simultaneous detection and segmentation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 297–312. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10584-0_20
Hariharan, B., Arbelaez, P., Girshick, R., Malik, J.: Hypercolumns for object segmentation and fine-grained localization. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, pp. 447–456 (2015). https://doi.org/10.1109/CVPR.2015.7298642
Dai, J., He, K., Sun, J.: Instance-aware semantic segmentation via multi-task network cascades. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, pp. 3150–3158 (2016). https://doi.org/10.1109/CVPR.2016.343
He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. In: 2017 IEEE International Conference on Computer Vision (ICCV), Venice, pp. 2980–2988 (2017). https://doi.org/10.1109/ICCV.2017.322
Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 664–676 (2017). https://doi.org/10.1109/TPAMI.2016.2598339
Kang, K., et al.: T-CNN: tubelets with convolutional neural networks for object detection from videos. IEEE Trans. Circuits Syst. Video Technol. 28(10), 2896–2907 (2018). https://doi.org/10.1109/TCSVT.2017.2736553
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015). https://doi.org/10.1038/nature14539
Chen, G., Cai, Z., Li, X.: Recognition and classification of high-resolution remote sensing image based on convolutional neural. Int. J. Performability Eng. 14(11), 2852–2863 (2018)
Chen, G., Cai, Z., Li, X.: Classification of remote sensing images based on distributed convolutional neural network model. Int. J. Performability Eng. 15(6), 1508–1517 (2019)
Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. In: NIPS, vol. 25. Curran Associates Inc. (2012)
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Region-based convolutional networks for accurate object detection and segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 38(1), 142–158 (2016). https://doi.org/10.1109/TPAMI.2015.2437384
Lin, T., Goyal, P., Girshick, R., He, K., Dollar, P.: Focal loss for dense object detection. IEEE Trans. Pattern Anal. Mach. Intell. 42(2), 318–327 (2020). https://doi.org/10.1109/TPAMI.2018.2858826
Zhang, Z., Qiao, S., Xie, C., Shen, W., Wang, B., Yuille, A.: Single-shot object detection with enriched semantics. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, pp. 5813–5821 (2018). https://doi.org/10.1109/CVPR.2018.00609
Lyu, S., Cai, X., Feng, R.: YOLOv3 network based on improved loss function. Comput. Syst. Appl. 28(2), 1–7 (2019). https://doi.org/10.15888/j.cnki.csa.006772
Li, Y., Hou, L., Wang, C.: Moving objects detection in automatic driving based on YOLOv3. Comput. Eng. Des. 40(4) (2019)
Jin, Y., Luo, N.: Improved YOLOv2 vehicle real-time detection algorithm combined with multi-scale features. Comput. Eng. Des. 40(05) (2019)
Oksuz, K., Cam, B., Kalkan, S., Akbas, E.: Imbalance problems in object detection: a review. IEEE Trans. Pattern Anal. Mach. Intell. (2021). https://doi.org/10.1109/TPAMI.2020.2981890
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chen, G., Wang, Q., Li, Q., Hu, J., Liu, J. (2023). Solving Class Imbalance Problem in Target Detection with a Squared Cross Entropy Based Method. In: Huang, DS., Premaratne, P., Jin, B., Qu, B., Jo, KH., Hussain, A. (eds) Advanced Intelligent Computing Technology and Applications. ICIC 2023. Lecture Notes in Computer Science, vol 14087. Springer, Singapore. https://doi.org/10.1007/978-981-99-4742-3_10
Download citation
DOI: https://doi.org/10.1007/978-981-99-4742-3_10
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-4741-6
Online ISBN: 978-981-99-4742-3
eBook Packages: Computer ScienceComputer Science (R0)