• Corpus ID: 58028958

Scale-Aware Attention Network for Crowd Counting

@article{Varior2019ScaleAwareAN,
  title={Scale-Aware Attention Network for Crowd Counting},
  author={Rahul Rama Varior and Bing Shuai and Joseph Tighe and Davide Modolo},
  journal={ArXiv},
  year={2019},
  volume={abs/1901.06026}
}
In crowd counting datasets, people appear at different scales, depending on their distance to the camera. To address this issue, we propose a novel multi-branch scale-aware attention network that exploits the hierarchical structure of convolutional neural networks and generates, in a single forward pass, multi-scale density predictions from different layers of the architecture. To aggregate these maps into our final prediction, we present a new soft attention mechanism that learns a set of… 

Figures and Tables from this paper

PDANet: Pyramid Density-aware Attention Net for Accurate Crowd Counting
TLDR
Extensive evaluations conducted on the challenging benchmark datasets well demonstrate the superior performance of the proposed PDANet in terms of the accuracy of counting and generated density maps over the well-known state of the arts.
PSCNet: Pyramidal Scale and Global Context Guided Network for Crowd Counting
TLDR
A novel crowd counting approach based on pyramidal scale module (PSM) and global context module (GCM), dubbed PSCNet is proposed, which relieves non-uniform density distribution in crowds to a certain extent.
Pyramid Scale Network for Crowd Counting
TLDR
This paper proposes a novel crowd counting framework called Pyramid Scale Network (PSNet), which is the first work to explicitly address scale limitation and feature similarity in multi-column design.
Exploit the potential of Multi-column architecture for Crowd Counting
TLDR
This paper proposes a novel crowd counting framework called Pyramid Scale Network (PSNet), which is the first work to explicitly address scale limitation and feature similarity in multi-column design.
MSNet: multi-scale network for crowd counting
TLDR
A novel multi-scale network called MSNet is proposed which aims to maintain continuous variations and count the number of pedestrians accurately and is Inspired by the knowledge that using multiple small receptive field kernels to replace a single large receptive field will get a better performance.
Understanding the impact of mistakes on background regions in crowd counting
TLDR
A popular crowd counting network is enriched with a segmentation branch trained to suppress background predictions and this simple addition reduces background error by 10-83%, reduces fore-ground error by up to 26% and improves overall crowd counting performance up to 20%.
Crowd Counting Using End-to-End Semantic Image Segmentation
TLDR
This paper proposed an end-to-end semantic segmentation framework for crowd counting in a dense crowded image based on semantic scene segmentation using an optimized convolutional neural network and successfully highlighted the foreground and suppressed the background part.
A Improved Generative Adversarial Networking Architectures for Crowd Counting
TLDR
This work proposes a IGAN(Improved Generative Adversarial Networking) architecture to solve the accuracy of generative density map and validates the preferable performance of the Improved GAN in the complex scene.
W-Net: Reinforced U-Net for Density Map Estimation
TLDR
A network for crowd counting is presented which reports state of the art results on crowd counting benchmarks and an independent decoding Reinforcement branch is proposed which helps the network converge much earlier and also enables the network to estimate density maps with high Structural Similarity Index (SSIM).
CNN-based Density Estimation and Crowd Counting: A Survey
TLDR
Over 220 works are surveyed to comprehensively and systematically study the crowd counting models, mainly CNN-based density map estimation methods to make reasonable inference and prediction for the future development of crowd counting and to provide feasible solutions for the problem of object counting in other fields.
...
...

References

SHOWING 1-10 OF 40 REFERENCES
Crowd Counting via Scale-Adaptive Convolutional Neural Network
TLDR
A scale-adaptive CNN (SaCNN) architecture with a backbone of fixed small receptive fields is proposed to improve the network generalization on crowd scenes with few pedestrians, where most representative approaches perform poorly on.
Single-Image Crowd Counting via Multi-Column Convolutional Neural Network
TLDR
With the proposed simple MCNN model, the method outperforms all existing methods and experiments show that the model, once trained on one dataset, can be readily transferred to a new dataset.
Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds
TLDR
A novel approach is proposed that simultaneously solves the problems of counting, density map estimation and localization of people in a given dense crowd image and significantly outperforms state-of-the-art on the new dataset, which is the most challenging dataset with the largest number of crowd annotations in the most diverse set of scenes.
Switching Convolutional Neural Network for Crowd Counting
TLDR
A novel crowd counting model that maps a given crowd scene to its density and switch convolutional neural network that leverages variation of crowd density within an image to improve the accuracy and localization of the predicted crowd count is proposed.
Scale Aggregation Network for Accurate and Efficient Crowd Counting
TLDR
A novel training loss, combining of Euclidean loss and local pattern consistency loss is proposed, which improves the performance of the model in the authors' experiments and achieves superior performance to state-of-the-art methods while with much less parameters.
CrowdNet: A Deep Convolutional Network for Dense Crowd Counting
TLDR
This work uses a combination of deep and shallow, fully convolutional networks to predict the density map for a given crowd image, and shows that this combination is used for effectively capturing both the high-level semantic information and the low-level features, necessary for crowd counting under large scale variations.
Crowd Counting via Adversarial Cross-Scale Consistency Pursuit
TLDR
A novel crowd counting (density estimation) framework called Adversarial Cross-Scale Consistency Pursuit (ACSCP) is proposed, which designs a novel scale-consistency regularizer which enforces that the sum up of the crowd counts from local patches is coherent with the overall count of their region union.
Crowd Counting with Deep Negative Correlation Learning
TLDR
This work proposes a new learning strategy to produce generalizable features by way of deep negative correlation learning (NCL), which deeply learn a pool of decorrelated regressors with sound generalization capabilities through managing their intrinsic diversities.
CNN-Based cascaded multi-task learning of high-level prior and density estimation for crowd counting
TLDR
A novel end-to-end cascaded network of CNNs to jointly learn crowd count classification and density map estimation achieves lower count error and better quality density maps as compared to the recent state-of-the-art methods.
Divide and Grow: Capturing Huge Diversity in Crowd Images with Incrementally Growing CNN
TLDR
A growing CNN which can progressively increase its capacity to account for the wide variability seen in crowd scenes is tackled, which achieves higher count accuracy on major crowd datasets and analyses the characteristics of specialties mined automatically by the proposed model.
...
...