SCAR: Spatial-/Channel-wise Attention Regression Networks for Crowd Counting

Abstract

Recently, crowd counting is a hot topic in crowd analysis. Many CNN-based counting algorithms attain good performance. However, these methods only focus on the local appearance features of crowd scenes but ignore the large-range pixel-wise contextual and crowd attention information. To remedy the above problems, in this paper, we introduce the Spatial-/Channel-wise Attention Models into the traditional Regression CNN to estimate the density map, which is named as "SCAR". It consists of two modules, namely Spatial-wise Attention Model (SAM) and Channel-wise Attention Model (CAM). The former can encode the pixel-wise context of the entire image to more accurately predict density maps at the pixel level. The latter attempts to extract more discriminative features among different channels, which aids model to pay attention to the head region, the core of crowd scenes. Intuitively, CAM alleviates the mistaken estimation for background regions. Finally, two types of attention information and traditional CNN's feature maps are integrated by a concatenation operation. Furthermore, the extensive experiments are conducted on four popular datasets, Shanghai Tech Part A/B, GCC, and UCF_CC_50 Dataset. The results show that the proposed method achieves state-of-the-art results.

arXiv commentaccepted by Neurocomputing

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Sequence to Sequence Learning with Neural Networks
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Recurrent Models of Visual Attention
• Exploring Models and Data for Remote Sensing Image Caption Generation
• Weakly Supervised Adversarial Domain Adaptation for Semantic Segmentation in Urban Scenes
• C^3 Framework: An Open-source PyTorch Code for Crowd Counting

Cited by in corpus (24)

• NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization
• Focal Inverse Distance Transform Maps for Crowd Localization
• Distribution Matching for Crowd Counting
• CNN-based Density Estimation and Crowd Counting: A Survey
• Backbones-Review: Feature Extraction Networks for Deep Learning and Deep Reinforcement Learning Approaches
• DeepCorn: A Semi-Supervised Deep Learning Method for High-Throughput Image-Based Corn Kernel Counting and Yield Estimation
• Counting from Sky: A Large-scale Dataset for Remote Sensing Object Counting and A Benchmark Method
• NWPU-MOC: A Benchmark for Fine-grained Multi-category Object Counting in Aerial Images
• Counting Varying Density Crowds Through Density Guided Adaptive Selection CNN and Transformer Estimation
• Fast Video Crowd Counting with a Temporal Aware Network
• Learning Independent Instance Maps for Crowd Localization
• Vehicle Perception from Satellite
• AgRegNet: A Deep Regression Network for Flower and Fruit Density Estimation, Localization, and Counting in Orchards
• A Unified Multi-Task Learning Framework of Real-Time Drone Supervision for Crowd Counting
• Label-Aware Ranked Loss for robust People Counting using Automotive in-cabin Radar
• Feature-aware Adaptation and Density Alignment for Crowd Counting in Video Surveillance
• Domain-adaptive Crowd Counting via High-quality Image Translation and Density Reconstruction
• Focus on Semantic Consistency for Cross-domain Crowd Understanding
• Dense Point Prediction: A Simple Baseline for Crowd Counting and Localization
• CCCNet: An Attention Based Deep Learning Framework for Categorized Crowd Counting
• A Flow Base Bi-path Network for Cross-scene Video Crowd Understanding in Aerial View
• SPAP: Simultaneous Demand Prediction and Planning for Electric Vehicle Chargers in a New City
• Wisdom of (Binned) Crowds: A Bayesian Stratification Paradigm for Crowd Counting
• Region-Aware Network: Model Human's Top-Down Visual Perception Mechanism for Crowd Counting