Counting in the 2020s: Binned Representations and Inclusive Performance Measures for Deep Crowd Counting Approaches

TL;DR

This paper addresses the skewed data distribution in crowd counting datasets by introducing a binning-based training method and new performance measures, improving the robustness and evaluation of deep crowd counting models.

Contribution

It proposes a novel binning approach for balanced training and introduces inclusive performance metrics for better evaluation of crowd counting methods.

Findings

Binning-based training improves model robustness.

New performance measures provide more comprehensive evaluation.

Modified models outperform baselines on new metrics.

Abstract

The data distribution in popular crowd counting datasets is typically heavy tailed and discontinuous. This skew affects all stages within the pipelines of deep crowd counting approaches. Specifically, the approaches exhibit unacceptably large standard deviation wrt statistical measures (MSE, MAE). To address such concerns in a holistic manner, we make two fundamental contributions. Firstly, we modify the training pipeline to accommodate the knowledge of dataset skew. To enable principled and balanced minibatch sampling, we propose a novel smoothed Bayesian binning approach. More specifically, we propose a novel cost function which can be readily incorporated into existing crowd counting deep networks to encourage bin-aware optimization. As the second contribution, we introduce additional performance measures which are more inclusive and throw light on various comparative performance aspects of the deep networks. We also show that our binning-based modifications retain their superiority wrt the newly proposed performance measures. Overall, our contributions enable a practically useful and detail-oriented characterization of performance for crowd counting approaches.