Counting in the 2020s: Binned Representations and Inclusive Performance Measures for Deep Crowd Counting Approaches
This work addresses performance variability in crowd counting for computer vision applications, but it is incremental as it builds on existing deep networks with modifications.
The authors tackled the problem of heavy-tailed and discontinuous data distributions in crowd counting datasets, which cause large standard deviations in performance measures like MSE and MAE, by proposing a smoothed Bayesian binning approach and inclusive performance measures, resulting in improved and more detailed characterization of performance.
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.