Abstract
Recently, NMS-free detector has become a research hotspot to eliminate negative influences, while NMS-based detector mis-suppress objects in crowd scene. However, NMS-free may face the problem of sample imbalance that affects convergence. In this paper, Gaussian distribution is adopted to fit the distribution of the targets so that samples can be chosen according to it. And we propose Gaussian Balance Sampling strategy to balance positive and negative samples actively. Besides, a simple loss function, PDLoss, is proposed to eliminate duplicated matches on the label assignment procedure and increase training speed. In addition, by a novel Non-target Response Suppression method, the designed network can focus more on hard samples and improve model performance. With these techniques, the model achieved a competitive performance on the CrowdHuman dataset.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Chu, X., Zheng, A., Zhang, X., Sun, J.: Detection in crowded scenes: one proposal, multiple predictions. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12214–12223 (2020)
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Li, F.-F.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)
Ge, Z., Jie, Z., Huang, X., Xu, R., Yoshie, O.: PS-RCNN: detecting secondary human instances in a crowd via primary object suppression. In: 2020 IEEE International Conference on Multimedia and Expo (ICME), pp. 1–6. IEEE (2020)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Jonker, R., Volgenant, T.: Improving the Hungarian assignment algorithm. Oper. Res. Lett. 5(4), 171–175 (1986)
Lin, T.-Y., Goyal, P., He, K., Dollár, P.: Focal Loss for Dense Object Detection. Ross Girshick (2018)
Liu, S., Huang, D., Wang, Y.: Adaptive NMS: refining pedestrian detection in a crowd. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6459–6468 (2019)
Ren, S., He, K., Girshick, R., Sun, J.: Towards real-time object detection with region proposal networks. Faster R-CNN (2016)
Rukhovich, D., Sofiiuk, K., Galeev, D., Barinova, O., Konushin, A.: Iterdet: iterative scheme for object detection in crowded environments. arXiv preprint arXiv:2005.05708 (2020)
Shao, S., et al.: Crowdhuman: a benchmark for detecting human in a crowd. arXiv preprint arXiv:1805.00123 (2018)
Shrivastava, A., Gupta, A., Girshick, R.: Training region-based object detectors with online hard example mining. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 761–769 (2016)
Sun, P., Jiang, Y., Xie, E., Yuan, Z., Wang, C., Luo, P.: Onenet: towards end-to-end one-stage object detection. arXiv preprint arXiv:2012.05780 (2020)
Tian, Z., Shen, C., Chen, H., He, T.: Fully convolutional one-stage object detection. FCOS (2019)
Wang, J., Song, L., Li, Z., Sun, H., Sun, J., Zheng, N.: End-to-end object detection with fully convolutional network. arXiv preprint arXiv:2012.03544 (2020)
Wang, X., Xiao, T., Jiang, Y., Shao, S., Sun, J., Shen, C.: Repulsion loss: detecting pedestrians in a crowd. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7774–7783 (2018)
Wu, Y., Kirillov, A., Massa, F., Lo, W.-Y., Girshick, R.: Detectron2. https://github.com/facebookresearch/detectron2 (2019)
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: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9759–9768 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 IFIP International Federation for Information Processing
About this paper
Cite this paper
Yang, Y. et al. (2022). Gaussian Balanced Sampling for End-to-End Pedestrian Detector. In: Shi, Z., Jin, Y., Zhang, X. (eds) Intelligence Science IV. ICIS 2022. IFIP Advances in Information and Communication Technology, vol 659. Springer, Cham. https://doi.org/10.1007/978-3-031-14903-0_34
Download citation
DOI: https://doi.org/10.1007/978-3-031-14903-0_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-14902-3
Online ISBN: 978-3-031-14903-0
eBook Packages: Computer ScienceComputer Science (R0)
