Crowd Density Estimation using Imperfect Labels

TL;DR

This paper investigates how imperfect labels affect crowd counting accuracy and proposes a system that generates and uses such labels to train more robust models, demonstrating improved resilience to annotation errors.

Contribution

It introduces a method to generate imperfect labels using a deep learning annotator and shows this improves model robustness against annotation errors.

Findings

The proposed scheme achieves accuracy close to models trained with perfect labels.

Crowd counting models exhibit robustness to annotation errors.

Analysis conducted on two models and two benchmark datasets.

Abstract

Density estimation is one of the most widely used methods for crowd counting in which a deep learning model learns from head-annotated crowd images to estimate crowd density in unseen images. Typically, the learning performance of the model is highly impacted by the accuracy of the annotations and inaccurate annotations may lead to localization and counting errors during prediction. A significant amount of works exist on crowd counting using perfectly labelled datasets but none of these explore the impact of annotation errors on the model accuracy. In this paper, we investigate the impact of imperfect labels (both noisy and missing labels) on crowd counting accuracy. We propose a system that automatically generates imperfect labels using a deep learning model (called annotator) which are then used to train a new crowd counting model (target model). Our analysis on two crowd counting models and two benchmark datasets shows that the proposed scheme achieves accuracy closer to that of the model trained with perfect labels showing the robustness of crowd models to annotation errors.