Abstract
Local counts, or the number of objects in a local area, is a continuous value by nature. Yet recent state-of-the-art methods show that formulating counting as a classification task performs better than regression. Through a series of experiments on carefully controlled synthetic data, we show that this counter-intuitive result is caused by imprecise ground truth local counts. Factors such as biased dot annotations and incorrectly matched Gaussian kernels used to generate ground truth counts introduce deviations from the true local counts. Standard continuous regression is highly sensitive to these errors, explaining the performance gap between classification and regression. To mitigate the sensitivity, we loosen the regression formulation from a continuous scale to a discrete ordering and propose a novel discrete-constrained (DC) regression. Applied to crowd counting, DC-regression is more accurate than both classification and standard regression on three public benchmarks. A similar advantage also holds for the age estimation task, verifying the overall effectiveness of DC-regression. Code is available at https://github.com/xhp-hust-2018-2011/dcreg.
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
Notes
- 1.
This work assumes a kernel size of \(4\sigma \) and use the terms ‘size’ and ‘\(\sigma \)’ interchangeably.
References
Gu, K., Yang, L., Yao, A.: Dive deeper into integral pose regression. In: International Conference on Learning Representations (ICLR) (2022)
Idrees, H., et al.: Composition loss for counting, density map estimation and localization in dense crowds. In: The European Conference on Computer Vision (ECCV), pp. 532–546 (2018)
Lempitsky, V., Zisserman, A.: Learning to count objects in images. In: Advances in Neural Information Processing Systems, vol. 23 (2010)
Li, R., Xian, K., Shen, C., Cao, Z., Lu, H., Hang, L.: Deep attention-based classification network for robust depth prediction. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11364, pp. 663–678. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-20870-7_41
Li, Y., Zhang, X., Chen, D.: CSRNet: dilated convolutional neural networks for understanding the highly congested scenes. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1091–1100 (2018)
Liu, L., Lu, H., Xiong, H., Xian, K., Cao, Z., Shen, C.: Counting objects by blockwise classification. IEEE Trans. Circuits Syst. Video Technol. 30(10), 3513–3527 (2019)
Liu, X., Yang, J., Ding, W., Wang, T., Wang, Z., Xiong, J.: Adaptive mixture regression network with local counting map for crowd counting. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12369, pp. 241–257. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58586-0_15
Ma, Z., Wei, X., Hong, X., Gong, Y.: Bayesian loss for crowd count estimation with point supervision. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6142–6151 (2019)
Ma, Z., Wei, X., Hong, X., Lin, H., Qiu, Y., Gong, Y.: Learning to count via unbalanced optimal transport. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 2319–2327 (2021)
Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483–499. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46484-8_29
Oñoro-Rubio, D., López-Sastre, R.J.: Towards perspective-free object counting with deep learning. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 615–629. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46478-7_38
Paul Cohen, J., Boucher, G., Glastonbury, C.A., Lo, H.Z., Bengio, Y.: Count-ception: counting by fully convolutional redundant counting. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 18–26 (2017)
Peyré, G., Cuturi, M., et al.: Computational optimal transport: with applications to data science. Found. Trends® Mach. Learn. 11(5–6), 355–607 (2019)
Shi, Z., Mettes, P., Snoek, C.G.: Counting with focus for free. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 4200–4209 (2019)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. Computer Science (2014)
Sindagi, V.A., Patel, V.M.: Multi-level bottom-top and top-bottom feature fusion for crowd counting. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1002–1012 (2019)
Sindagi, V.A., Yasarla, R., Patel, V.M.: JHU-crowd++: large-scale crowd counting dataset and a benchmark method. Technical report (2020)
Tian, Y., Lei, Y., Zhang, J., Wang, J.Z.: PaDNet: pan-density crowd counting. IEEE Trans. Image Process. 29, 2714–2727 (2019)
Tingting, Y., Junqian, W., Lintai, W., Yong, X.: Three-stage network for age estimation. CAAI Trans. Intell. Technol. 4(2), 122–126 (2019)
Wan, J., Chan, A.: Modeling noisy annotations for crowd counting. In: Advances in Neural Information Processing Systems, vol. 33 (2020)
Wan, J., Liu, Z., Chan, A.B.: A generalized loss function for crowd counting and localization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1974–1983 (2021)
Wang, B., Liu, H., Samara, D., Hoai, M.: Distribution matching for crowd counting. In: Conference on Neural Information Processing Systems (NeurIPS) (2020)
Wang, C., et al.: Uniformity in heterogeneity: diving deep into count interval partition for crowd counting. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3234–3242 (2021)
Xia, M., Zhang, X., Weng, L., Xu, Y., et al.: Multi-stage feature constraints learning for age estimation. IEEE Trans. Inf. Forensics Secur. 15, 2417–2428 (2020)
Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: European Conference on Computer Vision, pp. 466–481 (2018)
Xiong, H., Cao, Z., Lu, H., Madec, S., Liu, L., Shen, C.: TasselNetv2: in-field counting of wheat spikes with context-augmented local regression networks. Plant Methods 15(1), 1–14 (2019)
Xiong, H., Lu, H., Liu, C., Liu, L., Cao, Z., Shen, C.: From open set to closed set: counting objects by spatial divide-and-conquer. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8362–8371 (2019)
Zhang, C., Li, H., Wang, X., Yang, X.: Cross-scene crowd counting via deep convolutional neural networks. In: CVPR (2015)
Zhang, Y., Zhou, D., Chen, S., Gao, S., Ma, Y.: Single-image crowd counting via multi-column convolutional neural network. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 589–597 (2016)
Zhang, Y., Liu, L., Li, C., et al.: Quantifying facial age by posterior of age comparisons. arXiv preprint arXiv:1708.09687 (2017)
Acknowledgments
This research is supported by the Ministry of Education, Singapore, under its MOE Academic Research Fund Tier 2 (STEM RIE2025 MOE-T2EP20220-0015).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Xiong, H., Yao, A. (2022). Discrete-Constrained Regression for Local Counting Models. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13684. Springer, Cham. https://doi.org/10.1007/978-3-031-20053-3_36
Download citation
DOI: https://doi.org/10.1007/978-3-031-20053-3_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20052-6
Online ISBN: 978-3-031-20053-3
eBook Packages: Computer ScienceComputer Science (R0)