首页/论文/1808.07456

arXiv 1808.074562018-08-22cs.CV

Stacked Pooling: Improving Crowd Counting by Boosting Scale Invariance

Zhejiang University（浙江大学）；Southwest Jiaotong University（西南交通大学）；Carnegie Mellon University（卡内基梅隆大学）

Siyu Huang, Xi Li, Zhi-Qi Cheng, Zhongfei Zhang, Alexander Hauptmann

备注：: The code is available at http://github.com/siyuhuang/crowdcount-stackpool

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

In this work, we explore the cross-scale similarity in crowd counting scenario, in which the regions of different scales often exhibit high visual similarity. This feature is universal both within an image and across different images, indicating the importance of scale invariance of a crowd counting model. Motivated by this, in this paper we propose simple but effective variants of pooling module, i.e., multi-kernel pooling and stacked pooling, to boost the scale invariance of convolutional neural networks (CNNs), benefiting much the crowd density estimation and counting. Specifically, the multi-kernel pooling comprises of pooling kernels with multiple receptive fields to capture the responses at multi-scale local ranges. The stacked pooling is an equivalent form of multi-kernel pooling, while, it reduces considerable computing cost. Our proposed pooling modules do not introduce extra parameters into model and can easily take place of the vanilla pooling layer in implementation. In empirical study on two benchmark crowd counting datasets, the stacked pooling beats the vanilla pooling layer in most cases.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd

Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；GE Global Research（通用电气全球研究中心）；Macau University of Science and Technology（澳门科技大学）

Pedestrian detection in crowded scenes is a challenging problem since the pedestrians often gather together and occlude each other. In this paper, we propose a new occlusion-aware R-CNN (OR-CNN) to improve the detection accuracy in the crowd. Specifically, we design a new aggregation loss to enforce proposals to be close and locate compactly to the corresponding objects. Meanwhile, we use a new part occlusion-aware region of interest (PORoI) pooling unit to replace the RoI pooling layer in order to integrate the prior structure information of human body with visibility prediction into the netw…

2018-07-23cs.CV

Multi-Level Attentive Convoluntional Neural Network for Crowd Counting

Beijing University of Technology（北京工业大学）；China Agricultural University（中国农业大学）；JD Finance America Corporation（京东金融美国公司）

Recently the crowd counting has received more and more attention. Especially the technology of high-density environment has become an important research content, and the relevant methods for the existence of extremely dense crowd are not optimal. In this paper, we propose a multi-level attentive Convolutional Neural Network (MLAttnCNN) for crowd counting. We extract high-level contextual information with multiple different scales applied in pooling, and use multi-level attention modules to enrich the characteristics at different layers to achieve more efficient multi-scale feature fusion, whic…

2021-05-24cs.AIcs.CV

Multi-channel Deep Supervision for Crowd Counting

School of Computer Science（计算机学院）；Northwestern Polytechnical University（西北工业大学）

Crowd counting is a task worth exploring in modern society because of its wide applications such as public safety and video monitoring. Many CNN-based approaches have been proposed to improve the accuracy of estimation, but there are some inherent issues affect the performance, such as overfitting and details lost caused by pooling layers. To tackle these problems, in this paper, we propose an effective network called MDSNet, which introduces a novel supervision framework called Multi-channel Deep Supervision (MDS). The MDS conducts channel-wise supervision on the decoder of the estimation mod…

2021-03-17cs.CV

In Defense of Single-column Networks for Crowd Counting

Duke University（杜克大学）；Institute of North Electronic Equipment（北方电子设备研究所）

Crowd counting usually addressed by density estimation becomes an increasingly important topic in computer vision due to its widespread applications in video surveillance, urban planning, and intelligence gathering. However, it is essentially a challenging task because of the greatly varied sizes of objects, coupled with severe occlusions and vague appearance of extremely small individuals. Existing methods heavily rely on multi-column learning architectures to extract multi-scale features, which however suffer from heavy computational cost, especially undesired for crowd counting. In this pap…

2018-08-18cs.CV

尺度感知人群计数网络与标注误差校正

Scale-Aware Crowd Count Network with Annotation Error Correction

National Yang Ming Chiao Tung University（阳明交通大学）；University at Albany, SUNY（纽约州立大学奥尔巴尼分校）

提出尺度感知人群计数网络SACC-Net，通过空间变化高斯分布同时建模标注误差与尺度变化，并在四个公开数据集上超越现有方法。

2023-12-28cs.CV

Global Sum Pooling: A Generalization Trick for Object Counting with Small Datasets of Large Images

University of Saskatchewan（萨斯喀彻温大学）

In this paper, we explore the problem of training one-look regression models for counting objects in datasets comprising a small number of high-resolution, variable-shaped images. We illustrate that conventional global average pooling (GAP) based models are unreliable due to the patchwise cancellation of true overestimates and underestimates for patchwise inference. To overcome this limitation and reduce overfitting caused by the training on full-resolution images, we propose to employ global sum pooling (GSP) instead of GAP or fully connected (FC) layers at the backend of a convolutional netw…

2019-09-27cs.CV

更多相关论文收起更多论文

Multi-Task Deep Networks for Depth-Based 6D Object Pose and Joint Registration in Crowd Scenarios

Imperial College（帝国理工学院）

In bin-picking scenarios, multiple instances of an object of interest are stacked in a pile randomly, and hence, the instances are inherently subjected to the challenges: severe occlusion, clutter, and similar-looking distractors. Most existing methods are, however, for single isolated object instances, while some recent methods tackle crowd scenarios as post-refinement which accounts multiple object relations. In this paper, we address recovering 6D poses of multiple instances in bin-picking scenarios in depth modality by multi-task learning in deep neural networks. Our architecture jointly l…

2018-06-11cs.CV

RepSFNet：一种具有结构重参数化的单融合网络用于人群计数

RepSFNet : A Single Fusion Network with Structural Reparameterization for Crowd Counting

Department of Electro-Optical Engineering（电子光学工程系）；National Formosa University（国家Formosa大学）；Department of Electrical Engineering（电气工程系）；National Taipei University（国家台北大学）；College of Artificial Intelligence and Green Energy（人工智能与绿色能源学院）；National Yang Ming Chiao Tung University（国家阳明交通大学）

RepSFNet通过轻量级架构和重参数化技术，在保持精度的同时显著降低计算成本，适用于实时人群计数场景。

2026-01-28cs.CV

Beyond Counting: Comparisons of Density Maps for Crowd Analysis Tasks - Counting, Detection, and Tracking

For crowded scenes, the accuracy of object-based computer vision methods declines when the images are low-resolution and objects have severe occlusions. Taking counting methods for example, almost all the recent state-of-the-art counting methods bypass explicit detection and adopt regression-based methods to directly count the objects of interest. Among regression-based methods, density map estimation, where the number of objects inside a subregion is the integral of the density map over that subregion, is especially promising because it preserves spatial information, which makes it useful for…

2018-06-13cs.CV

Encoder-Decoder Based Convolutional Neural Networks with Multi-Scale-Aware Modules for Crowd Counting

Graduate School of Information Science and Technology Osaka University（大阪大学信息科学与技术研究生院）；Institute of Scientific and Industrial Research Osaka University（大阪大学科学与工业研究所）；Department of Computer Engineering Faculty of Engineering Chulalongkorn University（朱拉隆功大学工程学院计算机工程系）

In this paper, we propose two modified neural networks based on dual path multi-scale fusion networks (SFANet) and SegNet for accurate and efficient crowd counting. Inspired by SFANet, the first model, which is named M-SFANet, is attached with atrous spatial pyramid pooling (ASPP) and context-aware module (CAN). The encoder of M-SFANet is enhanced with ASPP containing parallel atrous convolutional layers with different sampling rates and hence able to extract multi-scale features of the target object and incorporate larger context. To further deal with scale variation throughout an input image…

2020-11-25cs.AIcs.CV

Graph2Kernel Grid-LSTM: A Multi-Cued Model for Pedestrian Trajectory Prediction by Learning Adaptive Neighborhoods

Nanyang Technological University（南洋理工大学）

Pedestrian trajectory prediction is a prominent research track that has advanced towards modelling of crowd social and contextual interactions, with extensive usage of Long Short-Term Memory (LSTM) for temporal representation of walking trajectories. Existing approaches use virtual neighborhoods as a fixed grid for pooling social states of pedestrians with tuning process that controls how social interactions are being captured. This entails performance customization to specific scenes but lowers the generalization capability of the approaches. In our work, we deploy \textit{Grid-LSTM}, a recen…

2020-07-08cs.CV

NAS-Count: Counting-by-Density with Neural Architecture Search

School of Electronic and Information Engineering, Beihang University（北京航空航天大学电子信息工程学院）；YouKu Cognitive and Intelligent Lab, Alibaba Group（阿里巴巴集团优酷认知与智能实验室）；Beihang University（北京航空航天大学）；Computer Science Department, Aberystwyth University（阿伯里斯特威斯大学计算机科学系）；Key Laboratory of Advanced Technologies for Near Space Information Systems, Ministry of Industry and Information Technology of China（中国工业和信息化部近空间信息技术重点实验室）；Beijing Advanced Innovation Center for Big Data-Based Precision Medicine（北京大数据精准医疗先进创新中心）；Department of Computer Science and Engineering, University at Buffalo（纽约州立大学布法罗分校计算机科学与工程系）

Most of the recent advances in crowd counting have evolved from hand-designed density estimation networks, where multi-scale features are leveraged to address the scale variation problem, but at the expense of demanding design efforts. In this work, we automate the design of counting models with Neural Architecture Search (NAS) and introduce an end-to-end searched encoder-decoder architecture, Automatic Multi-Scale Network (AMSNet). Specifically, we utilize a counting-specific two-level search space. The encoder and decoder in AMSNet are composed of different cells discovered from micro-level …

2020-08-13cs.CV

PP-LinkNet: Improving Semantic Segmentation of High Resolution Satellite Imagery with Multi-stage Training

Grabtaxi Holdings（Grab出租车控股公司）

Road network and building footprint extraction is essential for many applications such as updating maps, traffic regulations, city planning, ride-hailing, disaster response \textit{etc}. Mapping road networks is currently both expensive and labor-intensive. Recently, improvements in image segmentation through the application of deep neural networks has shown promising results in extracting road segments from large scale, high resolution satellite imagery. However, significant challenges remain due to lack of enough labeled training data needed to build models for industry grade applications. I…

2020-10-14cs.CVcs.LGeess.IV