Crowd Counting via Adversarial Cross-Scale Consistency Pursuit

By Zan Shen, Yi Xu, Bingbing Ni, Minsi Wang, Jianguo Hu, Xiaokang Yang. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018

349 citations recorded by the source corpus.

Crowd counting or density estimation is a challenging task in computer vision due to large scale variations, perspective distortions and serious occlusions, etc. Existing methods generally suffer from two issues: 1) the model averaging effects in multi-scale CNNs induced by the widely adopted $$ regression loss; and 2) inconsistent estimation across different scaled inputs. To explicitly address these issues, we propose a novel crowd counting (density estimation) framework called Adversarial Cross-Scale Consistency Pursuit (ACSCP). On one hand, a U-net structured generation network is designed to generate density map from input patch, and an adversarial loss is directly employed to shrink the solution onto a realistic subspace, thus attenuating the blurry effects of density map estimation. On the other hand, we design a novel scale-consistency regularizer which enforces that the sum up of the crowd counts from local patches (i.e., small scale) is coherent with the overall count of their region union (i.e., large scale). The above losses are integrated via a joint training scheme, so as to help boost density estimation performance by further exploring the collaboration between both objectives. Extensive experiments on four benchmarks have well demonstrated the effectiveness of the proposed innovations as well as the superior performance over prior art.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/5101de7052206087dc256660d72cb05d0553b24c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Context-Aware Crowd Counting (2018, methodology): “The regressors can be based on Random Forests [18], Gaussian Processes [7], or more recently Deep Nets [41, 42, 26, 31, 40, 36, 32, 24, 19, 30, 33, 22, 15, 28, 5], with most state-of-the-art approaches now relying on the latter.”
NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization (2020, background): “Especially, benefiting from the development of deep learning in computer vision, the counting performance on the datasets [6], [7], [8], [9] is continuously refreshed by Convolutional Neural Networks (CNN)-based methods [10], [11], [12], [13], [14].”
Deep Structural Contour Detection (2020, methodology): “[51], MCNN [52], Switch CNN [34], ACSCP [37], CSRnet [24], SA-Net [6], MAN [42] and RANet [50].”
Distribution Matching for Crowd Counting (2020, background): “Most recent works [20, 35, 15, 4, 31, 50, 27, 40, 29, 26, 54, 8, 25, 55, 61, 59, 17, 48, 21, 23, 30, 47, 53, 43, 37, 56, 18, 39, 24, 44, 42] are based on density map estimation, which has been shown to be more robust than detection-then-count and count regression approaches.”
Learning Multi-Level Density Maps for Crowd Counting (2020, background): “Adversarial cross-scale consistency pursuit (ACSCP) of Shen et al. [52] is even more complex.”
Attention Scaling for Crowd Counting (2020, methodology): “These methods have tried to exploit multi-scale feature fusion [49, 29, 35], multi-task learning [34, 30, 21], and the attention mechanism [45, 44, 19] to solve the above questions.”
JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method (2020, methodology): “most recent methods ([30] ,[32], [33], [58], [25]) have focused on other properties of the problem.”
Bayesian Loss for Crowd Count Estimation With Point Supervision (2019, neutral): “9 ACSCP [37] 75.”
Learning From Synthetic Data for Crowd Counting in the Wild (2019, background): “At present, many CNNand GAN-based methods [43, 31, 32, 33, 7] attain a phenomenal performance on the existing datasets.”