Learning From Synthetic Data for Crowd Counting in the Wild
Open accessAbstract
Recently, counting the number of people for crowd scenes is a hot topic because of its widespread applications (e.g. video surveillance, public security). It is a difficult task in the wild: changeable environment, large-range number of people cause the current methods can not work well. In addition, due to the scarce data, many methods suffer from over-fitting to a different extent. To remedy the above two problems, firstly, we develop a data collector and labeler, which can generate the synthetic crowd scenes and simultaneously annotate them without any manpower. Based on it, we build a large-scale, diverse synthetic dataset. Secondly, we propose two schemes that exploit the synthetic data to boost the performance of crowd counting in the wild: 1) pretrain a crowd counter on the synthetic data, then finetune it using the real data, which significantly prompts the model's performance on real data; 2) propose a crowd counting method via domain adaptation, which can free humans from heavy data annotations. Extensive experiments show that the first method achieves the state-of-the-art performance on four real datasets, and the second outperforms our baselines. The dataset and source code are available at https://gjy3035.github.io/GCC-CL/.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Domain adaptation could be useful for AIoT applications when deploying models to new scenarios or new working modes of machines [128], [203], [204], [205], [206], e.g., 'synthetic → real', 'daytime → nighttime' or 'clear → rainy'.
“Domain adaptation could be useful for AIoT applications when deploying models to new scenarios or new working modes of machines [128], [203], [204], [205], [206], e.g., 'synthetic → real', 'daytime → nighttime' or 'clear → rainy'.”
From Empowering things with intelligence: a survey of the progress, challenges, and opportunities in artificial intelligence of things (2021) · cites this paper as [128]
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 74,248 · see citing works
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · see citing works
Image quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892 · see citing works
Densely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566 · see citing works
Fully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834 · see citing works
Unpaired image-to-image translation using cycle-consistent adversarial networks
Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.244 · Cited by 23,602 · see citing works
Labaca-Castro, R. (2023) · Springer eBooks · doi:10.1007/978-3-658-40442-0_9 · Cited by 21,100 · see citing works
GAN（Generative Adversarial Nets）
淳司, 柴. (2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,268 · see citing works
Single-Image Crowd Counting via Multi-Column Convolutional Neural Network
Zhang, Y., Zhou, D., Chen, S., Gao, S., & Ma, Y. (2016) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2016.70 · Cited by 2,356 · see citing works
Ros, G., Sellart, L., Materzynska, J., Vazquez, D., & Lopez, A. M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.352 · Cited by 2,338 · see citing works
Playing for Data: Ground Truth from Computer Games
Richter, S. R., Vineet, V., Roth, S., & Koltun, V. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46475-6_7 · Cited by 1,928 · see citing works
CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes
Li, Y., Zhang, X., & Chen, D. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00120 · Cited by 1,794 · see citing works
Spatial as Deep: Spatial CNN for Traffic Scene Understanding
Pan, X., Shi, J., Luo, P., Wang, X., & Tang, X. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.12301 · Cited by 1,213 · see citing works
Privacy preserving crowd monitoring: Counting people without people models or tracking
Chan, A. B., Liang, J., & Vasconcelos, N. M. (2008) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2008.4587569 · Cited by 1,198 · see citing works
Cross-scene crowd counting via deep convolutional neural networks
Zhang, C., Li, H., Wang, X., & Yang, X. (2015) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2015.7298684 · Cited by 1,155 · see citing works
Multi-source Multi-scale Counting in Extremely Dense Crowd Images
Idrees, H., Saleemi, I., Seibert, C., & Shah, M. A. (2013) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2013.329 · Cited by 1,065 · see citing works
Switching Convolutional Neural Network for Crowd Counting
Sam, D. B., Surya, S., & Babu, R. V. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.429 · Cited by 1,017 · see citing works
Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds
Idrees, H., Tayyab, M., Athrey, K., Zhang, D., Al-Maadeed, S. A., Rajpoot, N., & Shah, M. A. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01216-8_33 · Cited by 891 · see citing works
Scale Aggregation Network for Accurate and Efficient Crowd Counting
Cao, X., Wang, Z., Zhao, Y., & Su, F. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01228-1_45 · Cited by 774 · see citing works
Generating High-Quality Crowd Density Maps Using Contextual Pyramid CNNs
Sindagi, V. A., & Patel, V. M. (2017) · IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.206 · Cited by 734 · see citing works
Feature Mining for Localised Crowd Counting
Chen, K., Loy, C. C., Gong, S., & Xiang, T. (2012) · British Machine Vision Conference (BMVC) · doi:10.5244/c.26.21 · Cited by 691 · see citing works
Driving in the Matrix: Can virtual worlds replace human-generated annotations for real world tasks?
Johnson‐Roberson, M., Barto, C., Mehta, R., Sridhar, S. N., Rosaen, K., & Vasudevan, R. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989092 · Cited by 649 · see citing works
CNN-Based cascaded multi-task learning of high-level prior and density estimation for crowd counting
Sindagi, V. A., & Patel, V. M. (2017) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2017.8078491 · Cited by 568 · see citing works
Richter, S. R., Hayder, Z., & Koltun, V. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.243 · Cited by 434 · see citing works
DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimation
Liu, J., Gao, C., Meng, D., & Hauptmann, A. G. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00545 · Cited by 423 · see citing works
Crowd Counting via Adversarial Cross-Scale Consistency Pursuit
Shen, Z., Xu, Y., Ni, B., Wang, M., Hu, J., & Yang, X. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00550 · Cited by 379 · see citing works
Crowd Analysis Using Computer Vision Techniques
Silveira Jacques Junior, J., Musse, S., & Jung, C. (2010) · IEEE Signal Processing Magazine · doi:10.1109/msp.2010.937394 · Cited by 343 · see citing works
Ranjan, V., Le, H., & Hoai, M. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01234-2_17 · Cited by 323 · see citing works
Leveraging Unlabeled Data for Crowd Counting by Learning to Rank
Liu, X., van de Weijer, J., & Bagdanov, A. D. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00799 · Cited by 322 · see citing works
Detecting Coherent Groups in Crowd Scenes by Multiview Clustering
Wang, Q., Chen, M., Nie, F., & Li, X. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2875002 · Cited by 301 · see citing works
Self-citationCrowd Counting with Deep Negative Correlation Learning
Shi, Z., Zhang, L., Liu, Y., et al. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00564 · Cited by 292 · see citing works
Divide and Grow: Capturing Huge Diversity in Crowd Images with Incrementally Growing CNN
Sam, D. B., Sajjan, N. N., Babu, R. V., & Srinivasan, M. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00381 · Cited by 250 · see citing works
Spatial As Deep: Spatial CNN for Traffic Scene UnderstandingPreprint
Pan, X., Zhan, X., Shi, J., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.06080 · Cited by 227 · see citing works
Domain Adaptation Through Synthesis for Unsupervised Person Re-identification
Bąk, S., Carr, P., & Lalonde, J. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01261-8_12 · Cited by 224 · see citing works
Multi-scale convolutional neural networks for crowd counting
Zeng, L., Xu, X., Cai, B., Qiu, S., & Zhang, T. (2017) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2017.8296324 · Cited by 222 · see citing works
Data-driven crowd analysis in videos
Rodriguez, M. D., Šivic, J., Laptev, I., & Audibert, J.-Y. (2011) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2011.6126374 · Cited by 211 · see citing works
Crowd Counting using Deep Recurrent Spatial-Aware Network
Liu, L., Wang, H., Li, G., Ouyang, W., & Lin, L. (2018) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/118 · Cited by 201 · see citing works
A Multiview-Based Parameter Free Framework for Group Detection
Li, X., Chen, M., Nie, F., & Wang, Q. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.11208 · Cited by 191 · see citing works
Self-citationFully Convolutional Crowd Counting on Highly Congested Scenes
Marsden, M. A., McGuinness, K., Little, S., et al. (2017) · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · doi:10.5220/0006097300270033 · Cited by 190 · see citing works
Data-Driven Crowd Understanding: A Baseline for a Large-Scale Crowd Dataset
Zhang, C., Kang, K., Li, H., Wang, X., Xie, R., & Yang, X. (2016) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2016.2542585 · Cited by 118 · see citing works
Deep Metric Learning for Crowdedness Regression
Wang, Q., Wan, J., & Yuan, Y. (2017) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2017.2703920 · Cited by 114 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Zhang, J., & Tao, D. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3039359 · Cited by 774 · see citing works
NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization
Wang, Q., Gao, J., Lin, W., & Li, X. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3013269 · Cited by 510 · see citing works
Self-citationCrowd Analysis in Video Surveillance: A Review
Tomar, A., Kumar, S., & Pant, B. (2022) · 2022 International Conference on Decision Aid Sciences and Applications (DASA) · doi:10.1109/dasa54658.2022.9765008 · Cited by 29 · see citing works
- Authors
- Wang, Q., Gao, J., Lin, W., & Yuan, Y.
- Affiliations
- Northwestern Polytechnical University (CN)
- Venue
- 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2019-06
- Pages
- 8190-8199
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2963693541
- Cited by
- 654
- References
- 42
- Citations by year
- 2026: 32 · 2025: 50 · 2024: 103 · 2023: 114 · 2022: 108 · 2021: 117 · 2020: 103 · 2019: 27
- FWCI
- 28.93
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (61632018, U1864204, 61773316)
- Natural Science Foundation of Shaanxi Province (U1864204, 2018KJXX‐024)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- crowd counting, synthetic data, synthetic data generation, data annotation, domain adaptation, pre-training and fine-tuning, overfitting, video surveillance
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
