Improving Object Counting with Heatmap Regulation

TL;DR

This paper introduces heatmap regulation (HR), a technique that enhances object counting models by regulating activation maps with coarse ground-truth data, leading to improved accuracy and state-of-the-art results across multiple datasets.

Contribution

The paper proposes heatmap regulation (HR), a novel method that improves one-look regression models for object counting by using coarse ground-truth activation maps.

Findings

HR suppresses false detections in counting models.

HR improves performance on all tested datasets.

Achieves state-of-the-art results in car counting.

Abstract

In this paper, we propose a simple and effective way to improve one-look regression models for object counting from images. We use class activation map visualizations to illustrate the drawbacks of learning a pure one-look regression model for a counting task. Based on these insights, we enhance one-look regression counting models by regulating activation maps from the final convolution layer of the network with coarse ground-truth activation maps generated from simple dot annotations. We call this strategy heatmap regulation (HR). We show that this simple enhancement effectively suppresses false detections generated by the corresponding one-look baseline model and also improves the performance in terms of false negatives. Evaluations are performed on four different counting datasets --- two for car counting (CARPK, PUCPR+), one for crowd counting (WorldExpo) and another for biological cell counting (VGG-Cells). Adding HR to a simple VGG front-end improves performance on all these benchmarks compared to a simple one-look baseline model and results in state-of-the-art performance for car counting.