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

TL;DR

This paper introduces a Bayesian stratification method for crowd counting that improves performance consistency across count ranges by balancing sampling and optimizing with a new cost function, leading to more reliable evaluation.

Contribution

It proposes a novel Bayesian stratification approach and a new cost function for crowd counting, enhancing performance analysis and robustness across different count levels.

Findings

Reduces error standard deviation in crowd counting models

Balances sampling across count strata for improved accuracy

Provides a nuanced performance analysis across datasets

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/