Learning to Count in the Crowd from Limited Labeled Data

TL;DR

This paper introduces a semi-supervised crowd counting method using Gaussian Processes to leverage limited labeled data and unlabeled data, improving performance and enabling synthetic-to-real transfer.

Contribution

It proposes a novel Gaussian Process-based iterative learning approach that reduces annotation needs and enhances generalization from synthetic to real-world datasets.

Findings

Effective semi-supervised counting on multiple datasets

Improved generalization from synthetic to real data

Reduces annotation effort significantly

Abstract

Recent crowd counting approaches have achieved excellent performance. However, they are essentially based on fully supervised paradigm and require large number of annotated samples. Obtaining annotations is an expensive and labour-intensive process. In this work, we focus on reducing the annotation efforts by learning to count in the crowd from limited number of labeled samples while leveraging a large pool of unlabeled data. Specifically, we propose a Gaussian Process-based iterative learning mechanism that involves estimation of pseudo-ground truth for the unlabeled data, which is then used as supervision for training the network. The proposed method is shown to be effective under the reduced data (semi-supervised) settings for several datasets like ShanghaiTech, UCF-QNRF, WorldExpo, UCSD, etc. Furthermore, we demonstrate that the proposed method can be leveraged to enable the network in learning to count from synthetic dataset while being able to generalize better to real-world datasets (synthetic-to-real transfer).