目标检测的损失函数研究进展
Research Progress of Loss Function in Object Detection
DOI: 10.12677/CSA.2021.1111288, PDF,  被引量    国家自然科学基金支持
作者: 杨倩会, 何 强, 王恒友：北京建筑大学理学院，北京；张长伦：北京建筑大学理学院，北京;北京建筑大学，北京未来城市设计高精尖创新中心，北京
关键词: 目标检测；损失函数；交并比；Ln范数；Object Detection； Loss Function； Intersection over Union； Ln Norm
摘要: 损失函数是目标检测中的一个研究热点。在深度学习飞速发展的过程中，目标检测算法取得众多研究成果，并广泛应用于人脸检测、门禁识别、自动驾驶等领域。为了进一步了解目标检测的发展细节，本文从目标检测的损失函数优化出发，梳理概括近年来目标检测中分类损失和回归损失的发展进程，并对其进行归类、分析。首先介绍分类损失的发展历程，然后介绍回归损失的两大发展方向：基于Ln范数与基于交并比(IoU)的损失函数，并分析这些损失函数的优缺点以及相互之间的关联性。最后，对基于目标检测的损失函数的未来发展方向进行展望。
Abstract: Loss function is a research hotspot in object detection. With the rapid development of deep learning, object detection algorithms have achieved many research results, and are widely used in face detection, access control recognition, and automatic driving and so forth. In order to further understand the development details of object detection, this article starts from the optimization of the loss function of object detection, combs and summarizes the development process of classification loss and regression loss in object detection in recent years, and classifies and analyzes them. First introduce the development history of classification loss, and then introduce the two major development directions of regression loss: loss function based on Ln norm and based on Intersection over Union (IoU), and analyze the advantages and disadvantages of these loss functions and the correlation between them. Finally, the future development direction of the loss function based on object detection is prospected.
文章引用：杨倩会, 张长伦, 何强, 王恒友. 目标检测的损失函数研究进展[J]. 计算机科学与应用, 2021, 11(11): 2836-2844. https://doi.org/10.12677/CSA.2021.1111288

参考文献

[1] Girshick, R., Donahue, J., Darrell, T., et al. (2014) Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. IEEE Conference on Computer Vision and Pattern Recognition, Columbus, 23-28 June 2014, 580-587. [Google Scholar] [CrossRef] 
[2] Girshick, R. (2015) Fast R-CNN. IEEE International Conference on Computer Vision (ICCV), Santiago, 7-13 December 2015, 1440-1448. [Google Scholar] [CrossRef] 
[3] Ren, S., He, K., Girshick, R., et al. (2015) Faster R-CNN: Towards Real-Time Object Detection with Region Pro-posal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 1137-1149. [Google Scholar] [CrossRef] 
[4] Cai, Z.W. and Vasconcelos, N. (2017) Cascade R-CNN: Delving into High Quality Object Detection. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 6154-6162. [Google Scholar] [CrossRef] 
[5] He, K.M., Georgia, G., Piotr, D., et al. (2018) Mask R-CNN. IEEE Transactions on Pattern Analysis & Machine Intelligence, 42, 386-397. [Google Scholar] [CrossRef] 
[6] Pang, J.M., Chen, K., Shi, J.P., et al. (2019) Libra R-CNN: Towards Balanced Learning for Object Detection. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recog-nition (CVPR), Long Beach, 15-20 June 2019, 821-830. [Google Scholar] [CrossRef] 
[7] Sun, P., Zhang, R.F., Jiang, Y., et al. (2021) Sparse R-CNN: End-to-End Object Detection with Learnable Proposals. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 20-25 June 2021, 14449-14458. [Google Scholar] [CrossRef] 
[8] Redmon, J., Divvala, S., Girshick, R., et al. (2016) You Only Look Once: Unified, Real-Time Object Detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 779-788. [Google Scholar] [CrossRef] 
[9] Redmon, J. and Farhadi, A. (2016) YOLO9000: Better, Faster, Stronger. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 6517-6525. [Google Scholar] [CrossRef] 
[10] Redmon, J. and Farhadi, A. (2018) YOLOv3: An In-cremental Improvement.
https://arxiv.org/abs/1804.02767
[11] Bochkovskiy, A., et al. (2020) YOLOv4: Optimal Speed and Accuracy of Object Detection.
https://arxiv.org/abs/2004.10934
[12] Liu, W., Anguelov, D., Erhan, D., et al. (2016) SSD: Single Shot Multi-Box Detector. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 21-37. [Google Scholar] [CrossRef] 
[13] Fu, C.Y., Liu, W., Ranga, A., et al. (2017) DSSD: Deconvolu-tional Single Shot Detector.
https://arxiv.org/abs/1701.06659
[14] Carion, N., Massa, F., Synnaeve, G., et al. End-to-End Object Detection with Transformers.
https://arxiv.org/abs/2005.12872
[15] 鲁晨光. Shannon公式改造[J]. 通信学报, 1991, 12(2): 95-96.
[16] Lin, T.Y., Goyal, P., Girshick, R., He, K.M., et al. (2018) Focal Loss for Dense Object Detection. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, 22-29 October 2017, 2999-3007. [Google Scholar] [CrossRef] 
[17] Yu, J.H., Jiang, Y., Wang, Z.Y., et al. (2016) Unitbox: An Advanced Object Detection Network. Proceedings of the 24th ACM International Conference on Multimedia, Amsterdam, 15-19 October 2016, 516-520. [Google Scholar] [CrossRef] 
[18] Rezatofighi, H., Tsoi, N., Gwak, J.Y., et al. (2019) Generalized Intersection over Union: A Metric and a Loss for Bounding Box Regression. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, 15-20 June 2019, 658-666. [Google Scholar] [CrossRef] 
[19] Zheng, Z., Wang, P., Liu, W., et al. (2020) Distance-IOU Loss: Faster and Better Learning for Bounding Box Re-gression. The Association for the Advance of Artificial Intelligence (AAAI), New York, 7-12 February 2020, 12993-13000.
[20] Zhang, Y.F., Ren, W.Q., Zhang, Z., et al. (2021) Focal and Efficient IOU Loss for Accurate Bounding Box Regression.
https://arxiv.org/abs/2101.08158