Distribution Matching for Crowd Counting

Abstract

In crowd counting, each training image contains multiple people, where each person is annotated by a dot. Existing crowd counting methods need to use a Gaussian to smooth each annotated dot or to estimate the likelihood of every pixel given the annotated point. In this paper, we show that imposing Gaussians to annotations hurts generalization performance. Instead, we propose to use Distribution Matching for crowd COUNTing (DM-Count). In DM-Count, we use Optimal Transport (OT) to measure the similarity between the normalized predicted density map and the normalized ground truth density map. To stabilize OT computation, we include a Total Variation loss in our model. We show that the generalization error bound of DM-Count is tighter than that of the Gaussian smoothed methods. In terms of Mean Absolute Error, DM-Count outperforms the previous state-of-the-art methods by a large margin on two large-scale counting datasets, UCF-QNRF and NWPU, and achieves the state-of-the-art results on the ShanghaiTech and UCF-CC50 datasets. DM-Count reduced the error of the state-of-the-art published result by approximately 16%. Code is available at https://github.com/cvlab-stonybrook/DM-Count.

arXiv commentNeurIPS 2020

References in corpus (3)

• NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization
• SCAR: Spatial-/Channel-wise Attention Regression Networks for Crowd Counting
• Top-Down Feedback for Crowd Counting Convolutional Neural Network

Cited by in corpus (13)

• Focal Inverse Distance Transform Maps for Crowd Localization
• Redesigning Multi-Scale Neural Network for Crowd Counting
• Counting Varying Density Crowds Through Density Guided Adaptive Selection CNN and Transformer Estimation
• TreeFormer: a Semi-Supervised Transformer-based Framework for Tree Counting from a Single High Resolution Image
• Cross-head Supervision for Crowd Counting with Noisy Annotations
• FusionCount: Efficient Crowd Counting via Multiscale Feature Fusion
• Backdoor Attacks on Crowd Counting
• Localization in the Crowd with Topological Constraints
• LDC-Net: A Unified Framework for Localization, Detection and Counting in Dense Crowds
• HDNet: A Hierarchically Decoupled Network for Crowd Counting
• Motion-guided Non-local Spatial-Temporal Network for Video Crowd Counting
• Coarse to Fine: Domain Adaptive Crowd Counting via Adversarial Scoring Network
• On the Visual-based Safe Landing of UAVs in Populated Areas: a Crucial Aspect for Urban Deployment