Leveraging Unlabeled Data for Crowd Counting by Learning to Rank

TL;DR

This paper introduces a crowd counting method that uses unlabeled images and a learning-to-rank framework to improve accuracy, addressing dataset limitations and achieving state-of-the-art results.

Contribution

It presents a novel approach combining learning-to-rank with crowd density estimation using unlabeled data, which enhances crowd counting performance.

Findings

Achieves state-of-the-art results on challenging datasets.

Effectively leverages unlabeled crowd images for training.

Demonstrates the benefit of ranking in crowd density estimation.

Abstract

We propose a novel crowd counting approach that leverages abundantly available unlabeled crowd imagery in a learning-to-rank framework. To induce a ranking of cropped images , we use the observation that any sub-image of a crowded scene image is guaranteed to contain the same number or fewer persons than the super-image. This allows us to address the problem of limited size of existing datasets for crowd counting. We collect two crowd scene datasets from Google using keyword searches and query-by-example image retrieval, respectively. We demonstrate how to efficiently learn from these unlabeled datasets by incorporating learning-to-rank in a multi-task network which simultaneously ranks images and estimates crowd density maps. Experiments on two of the most challenging crowd counting datasets show that our approach obtains state-of-the-art results.