Crowd Counting via Adversarial Cross-Scale Consistency Pursuit

Shen, Zan; Xu, Yi; Ni, Bingbing; Wang, Minsi; Hu, Jingyan; Yang, Xiaokang

doi:10.1109/cvpr.2018.00550

Cited by 328 publications

(211 citation statements)

References 20 publications

Supporting

Mentioning

210

Contrasting

Unclassified

Order By: Relevance

“…Crowd counting from a single image, especially in con-gested scenes, is a difficult problem since it suffers from multiple issues like high variability in scales, occlusions, perspective changes, background clutter, etc. Recently, several convolutional neural network (CNN) based methods [3,7,34,43,48,49,51,56,69,74] have attempted to address these issues with varying degree of successes. Among these issues, the problem of scale variation has particularly received considerable attention from the research community.…”

Section: Introductionmentioning

confidence: 99%

Multi-Level Bottom-Top and Top-Bottom Feature Fusion for Crowd Counting

Sindagi

Patel

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

182

View full text Add to dashboard Cite

Crowd counting presents enormous challenges in the form of large variation in scales within images and across the dataset. These issues are further exacerbated in highly congested scenes. Approaches based on straightforward fusion of multi-scale features from a deep network seem to be obvious solutions to this problem. However, these fusion approaches do not yield significant improvements in the case of crowd counting in congested scenes. This is usually due to their limited abilities in effectively combining the multi-scale features for problems like crowd counting. To overcome this, we focus on how to efficiently leverage information present in different layers of the network. Specifically, we present a network that involves: (i) a multilevel bottom-top and top-bottom fusion (MBTTBF) method to combine information from shallower to deeper layers and vice versa at multiple levels, (ii) scale complementary feature extraction blocks (SCFB) involving cross-scale residual functions to explicitly enable flow of complementary features from adjacent conv layers along the fusion paths. Furthermore, in order to increase the effectiveness of the multi-scale fusion, we employ a principled way of generating scale-aware ground-truth density maps for training. Experiments conducted on three datasets that contain highly congested scenes (ShanghaiTech, UCF CROWD 50, and UCF-QNRF) demonstrate that the proposed method is able to outperform several recent methods in all the datasets.

show abstract

Section: Introductionmentioning

confidence: 99%

Multi-Level Bottom-Top and Top-Bottom Feature Fusion for Crowd Counting

Sindagi

Patel

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

182

View full text Add to dashboard Cite

show abstract

“…In [15], Li et al propose to increment the receptive field size in CNN to better leverage multi-scale information. In addition to these specific network designs for implicitly handling the multiscale problem, Shen et al [24] introduce an ad hoc term in the training loss function in order to pursue the cross-scale consistency. In [11], Idrees et al propose to adopt variant ground-truth density map representation with Gaussian kernels of different sizes to better deal with density map es- Figure 2.…”

Section: Related Workmentioning

confidence: 99%

Learn to Scale: Generating Multipolar Normalized Density Maps for Crowd Counting

Qiu

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

140

View full text Add to dashboard Cite

Dense crowd counting aims to predict thousands of human instances from an image, by calculating integrals of a density map over image pixels. Existing approaches mainly suffer from the extreme density variances. Such density pattern shift poses challenges even for multi-scale model ensembling. In this paper, we propose a simple yet effective approach to tackle this problem. First, a patch-level density map is extracted by a density estimation model and further grouped into several density levels which are determined over full datasets. Second, each patch density map is automatically normalized by an online center learning strategy with a multipolar center loss. Such a design can significantly condense the density distribution into several clusters, and enable that the density variance can be learned by a single model. Extensive experiments demonstrate the superiority of the proposed method. Our work outperforms the state-of-the-art by 4.Sparse Medium Dense (a) Shanghai-B Shanghai-A UCF_CC_50 UCF-QNRF Dataset 0.00 0.05 0.10 0.15 0.20 0.25 0.30 0.35 Mean Relative Error MRE Overview Ours MCNN [33] Switch-CNN [23] CMTL [27] ACSCP [24] SANet [3] CSRNet [15] CP-CNN [28] L2R [18] D-ConvNet-v1 [25] ic-CNN [22] arXiv:1907.12428v2 [cs.CV]

show abstract

“…Recently, researchers have adopted deep learning-based methods instead of relying on hand-crafted features to generate high-quality density maps and achieve accurate crowd counting [3], [27]. These approaches can be applied to count different kinds of objects (i.e., vehicles and cells) instead of people [15], [9].…”

Section: Deep Learning-based Approachesmentioning

confidence: 99%

Crowd Counting on Images with Scale Variation and Isolated Clusters

Bai

Song

Chan

2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

Crowd counting is to estimate the number of objects (e.g., people or vehicles) in an image of unconstrained congested scenes. Designing a general crowd counting algorithm applicable to a wide range of crowd images is challenging, mainly due to the possibly large variation in object scales and the presence of many isolated small clusters. Previous approaches based on convolution operations with multi-branch architecture are effective for only some narrow bands of scales, and have not captured the longrange contextual relationship due to isolated clustering. To address that, we propose SACANet, a novel scale-adaptive long-range context-aware network for crowd counting.SACANet consists of three major modules: the pyramid contextual module which extracts long-range contextual information and enlarges the receptive field, a scaleadaptive self-attention multi-branch module to attain high scale sensitivity and detection accuracy of isolated clusters, and a hierarchical fusion module to fuse multi-level self-attention features. With group normalization, SACANet achieves better optimality in the training process. We have conducted extensive experiments using the VisDrone2019 People dataset, the VisDrone2019 Vehicle dataset, and some other challenging benchmarks. As compared with the stateof-the-art methods, SACANet is shown to be effective, especially for extremely crowded conditions with diverse scales and scattered clusters, and achieves much lower MAE as compared with baselines.

show abstract

Crowd Counting via Adversarial Cross-Scale Consistency Pursuit

Cited by 328 publications

References 20 publications

Multi-Level Bottom-Top and Top-Bottom Feature Fusion for Crowd Counting

Multi-Level Bottom-Top and Top-Bottom Feature Fusion for Crowd Counting

Learn to Scale: Generating Multipolar Normalized Density Maps for Crowd Counting

Crowd Counting on Images with Scale Variation and Isolated Clusters

Contact Info

Product

Resources

About