Uniformity in Heterogeneity:Diving Deep into Count Interval Partition for Crowd Counting

TL;DR

This paper introduces a novel approach for crowd counting by predicting count interval bins using the Uniform Error Partition and Mean Count Proxies criteria, leading to improved accuracy and state-of-the-art results.

Contribution

It proposes the first classification-based crowd counting method with theoretically grounded interval partitioning and discretization error minimization.

Findings

Achieves state-of-the-art performance on multiple datasets.

Demonstrates the effectiveness of UEP and MCP criteria.

Provides a new perspective on count interval partitioning in crowd counting.

Abstract

Recently, the problem of inaccurate learning targets in crowd counting draws increasing attention. Inspired by a few pioneering work, we solve this problem by trying to predict the indices of pre-defined interval bins of counts instead of the count values themselves. However, an inappropriate interval setting might make the count error contributions from different intervals extremely imbalanced, leading to inferior counting performance. Therefore, we propose a novel count interval partition criterion called Uniform Error Partition (UEP), which always keeps the expected counting error contributions equal for all intervals to minimize the prediction risk. Then to mitigate the inevitably introduced discretization errors in the count quantization process, we propose another criterion called Mean Count Proxies (MCP). The MCP criterion selects the best count proxy for each interval to represent its count value during inference, making the overall expected discretization error of an image nearly negligible. As far as we are aware, this work is the first to delve into such a classification task and ends up with a promising solution for count interval partition. Following the above two theoretically demonstrated criterions, we propose a simple yet effective model termed Uniform Error Partition Network (UEPNet), which achieves state-of-the-art performance on several challenging datasets. The codes will be available at: https://github.com/TencentYoutuResearch/CrowdCounting-UEPNet.