PaDNet: Pan-Density Crowd Counting

Tian, Yukun; Lei, Yiming; Zhang, Junping; Wang, James

doi:10.1109/tip.2019.2952083

Cited by 109 publications

(53 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Results are shown inTable 7. Our method surpasses S-DCNet and the previous best method, PaDNet[45], with 12.2% and 3.4% relative improvements in MAE, respectively. the longer side equals to 10000, to process the whole image.…”

mentioning

confidence: 81%

From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer

Xiong

Liu

et al. 2019

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

164

107

View full text Add to dashboard Cite

Visual counting, a task that aims to estimate the number of objects from an image/video, is an open-set problem by nature, i.e., the number of population can vary in [0, +∞) in theory. However, collected data and labeled instances are limited in reality, which means that only a small closed set is observed. Existing methods typically model this task in a regression manner, while they are prone to suffer from an unseen scene with counts out of the scope of the closed set. In fact, counting has an interesting and exclusive property-spatially decomposable. A dense region can always be divided until sub-region counts are within the previously observed closed set. We therefore introduce the idea of spatial divide-and-conquer (S-DC) that transforms open-set counting into a closed-set problem. This idea is implemented by a novel Supervised Spatial Divide-and-Conquer Network (SS-DCNet). Thus, SS-DCNet can only learn from a closed set but generalize well to open-set scenarios via S-DC. SS-DCNet is also efficient. To avoid repeatedly computing sub-region convolutional features, S-DC is executed on the feature map instead of on the input image. We provide theoretical analyses as well as a controlled experiment on toy data, demonstrating why closed-set modeling makes sense. Extensive experiments show that SS-DCNet achieves the state-of-the-art performance on three crowd counting datasets (ShanghaiTech, UCF_CC_50 and UCF-QNRF), a vehicle counting dataset (TRANCOS) and a plant counting dataset (MTC), with a 7.7% relative improvement on the UCF-QNRF, 33.1% on the TRANCOS, and 26.4% on the MTC. SS-DCNet also reports the state-of-the-art cross-domain performance on crowd counting datasets. Particularly in the task from UCF-QNRF to ShanghaiTech Part_A, SS-DCNet even beats most existing models trained directly on the target domain. Code and models have been made available at: https://tinyurl.com/SS-DCNet.

show abstract

mentioning

confidence: 81%

From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer

Xiong

Liu

et al. 2019

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

164

107

View full text Add to dashboard Cite

show abstract

“…There are a lot of other attempts to further improve the scale invariance, including 1) study on the fusion of various scale information [22,40,45,46], 2) study on multiblob based scale aggregation networks [3,47], 3) design of scale-invariant convolutional or pooling layers [9,17,20,39,45], and 4) study on the automated scale adaptive networks [30,31,49]. Typically, Li et al [17] propose CSRNet that exploits dilated convolutional layers to enlarge receptive fields for boosting performance.…”

Section: Cnn-based Methodsmentioning

confidence: 99%

Learning Spatial Awareness to Improve Crowd Counting

Cheng

Dai

et al. 2019

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

138

View full text Add to dashboard Cite

The aim of crowd counting is to estimate the number of people in images by leveraging the annotation of center positions for pedestrians' heads. Promising progresses have been made with the prevalence of deep Convolutional Neural Networks. Existing methods widely employ the Euclidean distance (i.e., L 2 loss) to optimize the model, which, however, has two main drawbacks: (1) the loss has difficulty in learning the spatial awareness (i.e., the position of head) since it struggles to retain the high-frequency variation in the density map, and (2) the loss is highly sensitive to various noises in crowd counting, such as the zeromean noise, head size changes, and occlusions. Although the Maximum Excess over SubArrays (MESA) loss has been previously proposed by [16] to address the above issues by finding the rectangular subregion whose predicted density map has the maximum difference from the ground truth, it cannot be solved by gradient descent, thus can hardly be integrated into the deep learning framework. In this paper, we present a novel architecture called SPatial Awareness Network (SPANet) to incorporate spatial context for crowd counting. The Maximum Excess over Pixels (MEP) loss is proposed to achieve this by finding the pixel-level subregion with high discrepancy to the ground truth. To this end, we devise a weakly supervised learning scheme to generate such region with a multi-branch architecture. The proposed framework can be integrated into existing deep crowd counting methods and is end-to-end trainable. Extensive experiments on four challenging benchmarks show that our method can significantly improve the performance of baselines. More remarkably, our approach outperforms the state-of-the-art methods on all benchmark datasets.

show abstract

“…ASD [14] contributed to adaptability by proposing an adaptive scenario discovery framework to value the weights of two different density maps generated by sparse column and dense column. PaDNet [31] committed to taking full use of extracted features by captures the global and local feature.…”

Section: B Cnn-based Methodsmentioning

confidence: 99%

“…In [31], the global and local features are extracted from multi-scale features. While, we operate on the initial features generated by VGG16 to obtain the global context.…”

Section: B Cnn-based Methodsmentioning

confidence: 99%

Global Context Instructive Network for Extreme Crowd Counting

Wang

Wang²,

Bai

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Crowd counting has gained popularity due to wide applications, such as intelligent security, and urban planning. However, scale variation and perspective distortion make it a challenging task. Most existing works focus on multi-scale feature extraction to address the challenge of scale variation and perspective distortion. In this paper, we propose a novel Global Context Instructive Network (GCINet), which devotes to making full use of extracted features and obtaining precise counts. The main contributions are four folds. First, we construct a three-column Feature Processor to generate features with different scales. Second, an Instructive Module is proposed to introduce global context which is the substance for generating adaptive features. Based on global context, the three-column Feature Processor constitutes an adaptive feature generator. Third, a novel loss function which integrates Euclidean distance and spatial correlation is proposed to enhance the spatial correlation and consistency between pixels. We no longer regard a pixel as an independent point in the calculation, but consider the neighborhood space of the pixel to achieve complementary effects. Finally, we conduct experiments on ShanghaiTech dataset, UCF_CC_50 dataset, UCF_QNRF dataset and UCSD dataset which show that our approach achieves state-of-the-art performance. INDEX TERMS Crowd counting, density map, adaptive generator, global context instructive network (GCINet).

show abstract

PaDNet: Pan-Density Crowd Counting

Cited by 109 publications

References 48 publications

From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer

From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer

Learning Spatial Awareness to Improve Crowd Counting

Global Context Instructive Network for Extreme Crowd Counting

Contact Info

Product

Resources

About