Abstract
We introduce a novel tiny-object detection network that achieves better accuracy than existing detectors on TinyPerson dataset. It is an end-to-end detection framework developed on PaddlePaddle. A suit of strategies are developed to improve the detectors performance including: 1) data augmentation based on scale-match that aligns the object scales between the existing large-scale dataset and TinyPerson; 2) comprehensive training methods to further improve detection performance by a large margin; 3) model refinement based on the enhanced PAFPN module to fully utilize semantic information; 4) a hierarchical coarse-to-fine ensemble strategy to improve detection performance based on a well-designed model pond.
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
Similar content being viewed by others
References
Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: IEEE CVPR, pp. 6154–6162 (2018)
Girshick, R.B.: Fast R-CNN. In: IEEE ICCV, pp. 1440–1448 (2015)
J, H., L, S., J, S.: Squeeze-and-excitation networks. In: IEEE CVPR, pp. 7132–7141 (2014)
Lin, T., Dollár, P., Girshick, R.B., He, K., Hariharan, B., Belongie, S.J.: Feature pyramid networks for object detection. In: IEEE CVPR, pp. 936–944 (2017)
Gao, S., Cheng, M. M., Zhao, K.: Res2net: a new multi-scale backbone architecture. IEEE Trans. Pattern Anal. Mach. Intell. 43(2) (2019)
Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: IEEE CVPR, pp. 8759–8768 (2018)
Liu, Y., Wang, Y., Wang, S.: CBNet: a novel composite backbone network architecture for object detection. In: AAAI, pp. 11653–11660 (2020)
Yu, X., Gong, Y., Jiang, N., Ye, Q., Han, Z.: Scale match for tiny person detection. In: The IEEE Winter Conference on Applications of Computer Vision, pp. 1257–1265 (2020)
He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: ECCV, pp. 630–645 (2016)
PddlePaddle. https://github.com/PaddlePaddle/PaddleClas/
Hu, J., Shen, L., Albanie, S,, Sun, G., Wu, E.: Squeeze-and-excitation networks. In: IEEE CVPR, pp. 7132–7141 (2018)
Liu, Y., Wang, Y., Wang, S.: CBNet: a novel composite backbone network architecture for object detection. In: AAAI, pp. 11653–11660 (2020)
Acknowledgements
The work was supported in part by National Natural Science Foundation of China under Grants 62076016. This work is supported by Shenzhen Science and Technology Program KQTD2016112515134654. Baochang Zhang and Shumin Han are the correspondence authors.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Feng, Y. et al. (2020). Effective Feature Enhancement and Model Ensemble Strategies in Tiny Object Detection. In: Bartoli, A., Fusiello, A. (eds) Computer Vision – ECCV 2020 Workshops. ECCV 2020. Lecture Notes in Computer Science(), vol 12539. Springer, Cham. https://doi.org/10.1007/978-3-030-68238-5_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-68238-5_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-68237-8
Online ISBN: 978-3-030-68238-5
eBook Packages: Computer ScienceComputer Science (R0)