Abstract
Small object detection is a crucial task in computer vision due to its wide range of real-world applications. Detecting small objects accurately and efficiently remains a challenging task due to the reduced size of the objects, low contrast to their surroundings, and potential occlusions. To tackle this issue, we proposed a method for detecting small objects in object detection tasks, including a new strategy for balancing positive and negative samples, a loss function that adapts the weight of detection losses according to object size, and an anchor mechanism that accommodates objects with diverse sizes and aspect ratios. The experimental data substantiates that our method has achieved a 12.9% increase in average accuracy for small objects on the COCO dataset, compared to the baseline.
S. Zhang and Y. Sun—Contributed equally to this work.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. Cornell University - arXiv (2015)
Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) Computer Vision – ECCV 2014. ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48, https://www.microsoft.com/en-us/research/publication/microsoft-coco-common-objects-in-context/
Wang, Y., Zhang, X., Yang, T., Sun, J.: Anchor DETR: query design for transformer-based detector. In: Proceedings of the AAAI Conference on Artificial Intelligence (2021)
Huang, T., et al.: DyRep: bootstrapping training with dynamic re-parameterization. In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 578–587 (2022). https://doi.org/10.1109/CVPR52688.2022.00067
Liu, S., et al.: DAB-DETR: dynamic anchor boxes are better queries for DETR (2022). https://arxiv.org/abs/2201.12329
Kaul, P., Xie, W., Zisserman, A.: Label, verify, correct: a simple few shot object detection method. In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14217–14227 (2022). https://doi.org/10.1109/CVPR52688.2022.01384
Lim, J.-S., Astrid, M., Yoon, H.-J., Lee, S.-I.: Small object detection using context and attention. arXiv Computer Vision and Pattern Recognition (2019)
Wang, C., Wang, H., Pan, P.: Local contrast and global contextual information make infrared small object salient again (2023)
Xiangsuo, F., Wenlin, Q., Juliu, L., Qingnan, H., Fan, Z.: Dim and small target detection based on spatio-temporal filtering and high-order energy estimation. IEEE Photonics J. 15(2), 1–20 (2023). https://doi.org/10.1109/JPHOT.2023.3242991
Park, C.-W., Seo, Y., Sun, T.-J., Lee, G.-W., Huh, E.-N.: Small object detection technology using multi-modal data based on deep learning. In: 2023 International Conference on Information Networking (ICOIN), pp. 420–422 (2023). https://doi.org/10.1109/ICOIN56518.2023.10049014
Zhang, S., Chi, C., Yao, Y., Lei, Z., Li, S.Z.: Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9756–9765 (2020). https://doi.org/10.1109/CVPR42600.2020.00978
Kim, K., Lee, H.S.: Probabilistic anchor assignment with IoU prediction for object detection (2020). https://arxiv.org/abs/2007.08103
Wang, J., Chen, K., Yang, S., Loy, C.C., Lin, D.: Region proposal by guided anchoring. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2960–2969 (2019). https://doi.org/10.1109/CVPR.2019.00308
Acknowledgement
This work was supported by “Youth Innovative Research Team of Capital Normal University”, Project of High-level Teachers in Beijing Municipal Universities in the Period of 13th Five-year Plan CIT &TCD201804075 and STCSM 18DZ2270700.
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
Zhang, S., Sun, Y., Su, J., Gan, G., Wen, Z. (2023). Adaptive Training Strategies for Small Object Detection Using Anchor-Based Detectors. In: Iliadis, L., Papaleonidas, A., Angelov, P., Jayne, C. (eds) Artificial Neural Networks and Machine Learning – ICANN 2023. ICANN 2023. Lecture Notes in Computer Science, vol 14260. Springer, Cham. https://doi.org/10.1007/978-3-031-44195-0_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-44195-0_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44194-3
Online ISBN: 978-3-031-44195-0
eBook Packages: Computer ScienceComputer Science (R0)