Abstract
We focus on the construction of a loss function for the bounding box regression. The Intersection over Union (IoU) metric is improved to converge faster, to make the surface of the loss function smooth and continuous over the whole searched space, and to reach a more precise approximation of the labels. The main principle is adding a smoothing part to the original IoU, where the smoothing part is given by a linear space with values that increases from the ground truth bounding box to the border of the input image, and thus covers the whole spatial search space. We show the motivation and formalism behind this loss function and experimentally prove that it outperforms IoU, DIoU, CIoU, and SIoU by a large margin. We experimentally show that the proposed loss function is robust with respect to the noise in the dimension of ground truth bounding boxes. The reference implementation is available at https://gitlab.com/irafm-ai/smoothing-iou.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Gevorgyan, Z.: Siou loss: more powerful learning for bounding box regression. arXiv preprint arXiv:2205.12740 (2022)
Girshick, R.: Fast R-CNN. In: Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV). ICCV 2015, USA, pp. 1440–1448, IEEE Computer Society (2015). https://doi.org/10.1109/ICCV.2015.169
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2013). https://doi.org/10.1109/CVPR.2014.81
Huber, P.J.: Robust estimation of a location parameter. Ann. Math. Stat. 35, 492–518 (1964)
Jarrahi, M.H., Memariani, A., Guha, S.: The principles of data-centric AI (DCAI). arXiv preprint arXiv:2211.14611 (2022)
Lei, R., Yan, D., Wu, H., Peng, Y.: A precise convolutional neural network-based classification and pose prediction method for PCB component quality control. In: 2022 14th International Conference on Electronics, Computers and Artificial Intelligence (ECAI), pp. 1–6. IEEE (2022)
Li, G., Ji, Z., Qu, X., Zhou, R., Cao, D.: Cross-domain object detection for autonomous driving: a stepwise domain adaptative yolo approach. IEEE Trans. Intell. Veh. 7(3), 603–615 (2022)
Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
Müller, R., Kornblith, S., Hinton, G.E.: When does label smoothing help? In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Pal, S.K., Pramanik, A., Maiti, J., Mitra, P.: Deep learning in multi-object detection and tracking: state of the art. Appl. Intell. 51(9), 6400–6429 (2021). https://doi.org/10.1007/s10489-021-02293-7
Pang, J., Chen, K., Shi, J., Feng, H., Ouyang, W., Lin, D.: Libra r-cnn: Towards balanced learning for object detection. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 821–830. IEEE Computer Society (2019). https://doi.org/10.1109/CVPR.2019.00091, https://doi.ieeecomputersociety.org/10.1109/CVPR.2019.00091
Ravi, N., Naqvi, S., El-Sharkawy, M.: Biou: an improved bounding box regression for object detection. J. Low Power Electron. Appl. 12, 51 (2022). https://doi.org/10.3390/jlpea12040051
Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)
Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Cortes, C., Lawrence, N.D., Lee, D.D., Sugiyama, M., Garnett, R. (eds.) NIPS, pp. 91–99 (2015)
Rezatofighi, S.H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I.D., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. CoRR abs/1902.09630 (2019). http://arxiv.org/abs/1902.09630
Tan, M., Le, Q.: Efficientnetv2: smaller models and faster training. In: International conference on machine learning, pp. 10096–10106. PMLR (2021)
Xufei, W., Song, J.: ICIOU: improved loss based on complete intersection over union for bounding box regression. IEEE Access PP, 1–1 (2021). https://doi.org/10.1109/ACCESS.2021.3100414
Yu, J., Jiang, Y., Wang, Z., Cao, Z., Huang, T.: Unitbox: an advanced object detection network. In: Proceedings of the 24th ACM International Conference on Multimedia. MM 2016, New York, NY, USA, pp. 516–520. Association for Computing Machinery (2016). https://doi.org/10.1145/2964284.2967274, https://doi.org/10.1145/2964284.2967274
Zeiler, M.D.: Adadelta: an adaptive learning rate method. arXiv preprint arXiv:1212.5701 (2012)
Zhang, H., Chang, H., Ma, B., Wang, N., Chen, X.: Dynamic R-CNN: towards high quality object detection via dynamic training. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 260–275. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58555-6_16
Zhang, Y.F., Ren, W., Zhang, Z., Jia, Z., Wang, L., Tan, T.: Focal and efficient IOU loss for accurate bounding box regression. Neurocomputing 506, 146–157 (2022). https://doi.org/10.1016/j.neucom.2022.07.042, https://www.sciencedirect.com/science/article/pii/S0925231222009018
Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., Ren, D.: Distance-IOU loss: faster and better learning for bounding box regression. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 07, pp. 12993–13000 (2020). https://doi.org/10.1609/aaai.v34i07.6999, https://ojs.aaai.org/index.php/AAAI/article/view/6999
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Števuliáková, P., Hurtik, P. (2023). Intersection over Union with Smoothing for Bounding Box Regression. In: Rojas, I., Joya, G., Catala, A. (eds) Advances in Computational Intelligence. IWANN 2023. Lecture Notes in Computer Science, vol 14135. Springer, Cham. https://doi.org/10.1007/978-3-031-43078-7_17
Download citation
DOI: https://doi.org/10.1007/978-3-031-43078-7_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43077-0
Online ISBN: 978-3-031-43078-7
eBook Packages: Computer ScienceComputer Science (R0)