eLibrary
  • Home
  • Sources
  • Search
  • About

Annotation-Efficient Crowd Counting: A Survey with a Focus on Count-Level Weak Supervision

Yushan Xu, Minmin Li, Yanan Zhang, Qiankun Ji, Qiaoqiao Feng, Fucheng Zhang
Frontiers in Computing and Intelligent Systems, (2026), Vol.18, No.2, pp.36-45
Published: October 29, 2026
DOI: 10.54097/nkkgyk35
PDF: Download Full Text PDF
Abstract

The current crowd counting models are trained from point level head annotation but only the total crowd count is assessed. It is expensive to close this gap: It takes about 2, 000 human-hours to annotate UCF-QNRF. This survey covers the topic of annotation-free/annotation-efficient crowd counting methods particularly with count-level weak supervision, which train from only image-level counts. We categorize the literature by the level of annotation efficiency, and argue that there are a 4-tiered taxonomy and two annotated efficiency pathways—one to enhance the use of annotation, and the other to diminish the need for it. The first pathway includes annotation-efficient losses under point supervision and semi-supervised methods which utilize unlabeled images using uncertainty-aware teacher student training, ranking and surrogate tasks. The second focuses on weakly supervised methods at the count level – from early running ranking networks, MAPS, and MATT, to most recent transformer, MLP and hybrid architectures. On four benchmarks, it is compared with a semi-supervised method and the results demonstrate that count-level weak supervision is competitive to semi-supervision without any semantic location annotations, but with a performance gap to full supervision on dense datasets. With that said, the possibilities of merging distinct approaches to annotation, annotation noise, and foundation models are open challenges.

Keywords: Crowd Counting, Weakly Supervised Learning, Count-Level Supervision, Annotation Efficiency, Semi-Supervised Learning, Density Map Estimation
APA Citation: Yushan Xu, Minmin Li, Yanan Zhang, Qiankun Ji, Qiaoqiao Feng, Fucheng Zhang (2026). Annotation-Efficient Crowd Counting: A Survey with a Focus on Count-Level Weak Supervision. Frontiers in Computing and Intelligent Systems, 18(2), 36-45. https://doi.org/10.54097/nkkgyk35

References

  1. Wang, J., Gao, M., Li, Q., Kim, H., & Jeon, G. (2024). A survey on supervised, unsupervised, and semi-supervised approaches in crowd counting. CMC-Computers, Materials & Continua, 81(3), 3561–3582.
  2. Gao, G., Gao, J., Liu, Q., Wang, Q., & Wang, Y. (2020). CNN-based density estimation and crowd counting: A survey. arXiv preprint arXiv:2003.12783.
  3. Idrees, H., Tayyab, M., Athrey, K., Zhang, D., Al-Maadeed, S., Rajpoot, N., & Shah, M. (2018). Composition loss for counting, density map estimation and localization in dense crowds. In Proceedings of the European Conference on Computer Vision (ECCV) (pp. 532–546).
  4. Li, C., Hu, X., Abousamra, S., & Chen, C. (2023). Calibrating uncertainty for semi-supervised crowd counting. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (pp. 16731–16741).
  5. Wang, Q., Gao, J., Lin, W., & Li, X. (2021). NWPU-Crowd: A large-scale benchmark for crowd counting and localization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(6), 2141–2149.
  6. Lei, Y., Liu, Y., Zhang, P., & Liu, L. (2021). Towards using count-level weak supervision for crowd counting. Pattern Recognition, 109, 107616.
  7. Liu, Y., Liu, L., Wang, P., Zhang, P., & Lei, Y. (2020). Semi-supervised crowd counting via self-training on surrogate tasks. In Proceedings of the European Conference on Computer Vision (ECCV) (pp. 242–259).
  8. Song, Q., Wang, C., Jiang, Z., Wang, Y., Tai, Y., Wang, C., Li, J., Huang, F., & Wu, Y. (2021). Rethinking counting and localization in crowds: A purely point-based framework. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (pp. 3365–3374).
  9. Lempitsky, V., & Zisserman, A. (2010). Learning to count objects in images. In Advances in Neural Information Processing Systems (NeurIPS) (pp. 1324–1332).
  10. Zhang, Y., Zhou, D., Chen, S., Gao, S., & Ma, Y. (2016). Single-image crowd counting via multi-column convolutional neural network. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 589–597).
  11. Yang, Y., Li, G., Wu, Z., Su, L., Huang, Q., & Sebe, N. (2020). Weakly-supervised crowd counting learns from sorting rather than locations. In Proceedings of the European Conference on Computer Vision (ECCV) (pp. 1–17).
  12. Li, Y., Zhang, X., & Chen, D. (2018). CSRNet: Dilated convolutional neural networks for understanding the highly congested scenes. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1091–1100).
  13. Ma, Z., Wei, X., Hong, X., & Gong, Y. (2019). Bayesian loss for crowd count estimation with point supervision. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (pp. 6142–6151).
  14. Wang, B., Liu, H., Samaras, D., & Hoai, M. (2020). Distribution matching for crowd counting. In Advances in Neural Information Processing Systems (NeurIPS) (Vol. 33, pp. 1595–1607).
  15. Meng, Y., Zhang, H., Zhao, Y., Yang, X., Qian, X., Huang, X., & Zheng, Y. (2021). Spatial uncertainty-aware semi-supervised crowd counting. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (pp. 15529–15539).
  16. Liang, D., Chen, X., Xu, W., Zhou, Y., & Bai, X. (2022). TransCrowd: Weakly-supervised crowd counting with transformers. Science China Information Sciences, 65(6), 160104.
  17. Wang, M., Zhou, J., Cai, H., & Gong, M. (2023). CrowdMLP: Weakly-supervised crowd counting via multi-granularity MLP. Pattern Recognition, 144, 109830.
  18. Wang, F., Liu, K., Wei, N., Sang, N., Xia, X., & Sang, J. (2026). Weakly supervised crowd counting with joint CNN and transformer network. Pattern Recognition, 171, 112077.
  19. Liu, X., van de Weijer, J., & Bagdanov, A. D. (2018). Leveraging unlabeled data for crowd counting by learning to rank. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 7661–7669).
  20. Wan, J., & Chan, A. B. (2020). Modeling noisy annotations for crowd counting. In Advances in Neural Information Processing Systems (NeurIPS) (Vol. 33, pp. 3386–3396).
  21. Liu, C., Lu, H., Cao, Z., & Liu, T. (2023). Point-query quadtree for crowd counting, localization, and more. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (pp. 1676–1685).
  22. Chen, I.-H., Chen, W.-T., Liu, Y.-W., Yang, M.-H., & Kuo, S.-Y. (2024). Improving point-based crowd counting and localization based on auxiliary point guidance. In Proceedings of the European Conference on Computer Vision (ECCV) (pp. 428–444).
  23. Savner, S. S., & Kanhangad, V. (2023). CrowdFormer: Weakly-supervised crowd counting with improved generalizability. Journal of Visual Communication and Image Representation, 94, 103853.
  24. Savner, S. S., & Kanhangad, V. (2025). CrowdNeXt: Boosting weakly supervised crowd counting with dual-path feature aggregation and a robust loss function. IEEE Transactions on Instrumentation and Measurement, 74, 1–16.
  25. Gao, M., Deng, M., Zhao, H., Chen, Y., & Chen, Y. (2024). Improving MLP-based weakly supervised crowd-counting network via scale reasoning and ranking. Electronics, 13(3), 471.
  26. Idrees, H., Saleemi, I., Seibert, C., & Shah, M. (2013). Multi-source multi-scale counting in extremely dense crowd images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 2547–2554).
  27. Sindagi, V. A., Yasarla, R., & Patel, V. M. (2022). JHU-Crowd++: Large-scale crowd counting dataset and a benchmark method. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(5), 2594–2609.
  28. Xu, Y., Zhong, Z., Lian, D., Li, J., Li, Z., Xu, X., & Gao, S. (2021). Crowd counting with partial annotations in an image. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (pp. 15570–15579).
  29. Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., & Sutskever, I. (2021). Learning transferable visual models from natural language supervision. In Proceedings of the International Conference on Machine Learning (ICML) (pp. 8748–8763).
  30. Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A. C., Lo, W.-Y., Dollár, P., & Girshick, R. (2023). Segment anything. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (pp. 4015–4026).
  31. Liang, D., Xie, J., Zou, Z., Ye, X., Xu, W., & Bai, X. (2023). CrowdCLIP: Unsupervised crowd counting via vision-language model. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 2893–2903).
© 2026 eLibrary · Stand on the shoulders of giants