Wisdom of (Binned) Crowds: A Bayesian Stratification Paradigm for Crowd Counting

Abstract

Datasets for training crowd counting deep networks are typically heavy-tailed in count distribution and exhibit discontinuities across the count range. As a result, the de facto statistical measures (MSE, MAE) exhibit large variance and tend to be unreliable indicators of performance across the count range. To address these concerns in a holistic manner, we revise processes at various stages of the standard crowd counting pipeline. To enable principled and balanced minibatch sampling, we propose a novel smoothed Bayesian sample stratification approach. We propose a novel cost function which can be readily incorporated into existing crowd counting deep networks to encourage strata-aware optimization. We analyze the performance of representative crowd counting approaches across standard datasets at per strata level and in aggregate. We analyze the performance of crowd counting approaches across standard datasets and demonstrate that our proposed modifications noticeably reduce error standard deviation. Our contributions represent a nuanced, statistically balanced and fine-grained characterization of performance for crowd counting approaches. Code, pretrained models and interactive visualizations can be viewed at our project page https://deepcount.iiit.ac.in/

arXiv commentAccepted at ACM Multimedia (ACMMM) 2021 . Code, pretrained models and interactive visualizations can be viewed at our project page https://deepcount.iiit.ac.in/

References in corpus (5)

• NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization
• SCAR: Spatial-/Channel-wise Attention Regression Networks for Crowd Counting
• CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes
• Dual Path Multi-Scale Fusion Networks with Attention for Crowd Counting
• Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds