Active Crowd Counting with Limited Supervision

by   Zhen Zhao, et al.

To learn a reliable people counter from crowd images, head center annotations are normally required. Annotating head centers is however a laborious and tedious process in dense crowds. In this paper, we present an active learning framework which enables accurate crowd counting with limited supervision: given a small labeling budget, instead of randomly selecting images to annotate, we first introduce an active labeling strategy to annotate the most informative images in the dataset and learn the counting model upon them. The process is repeated such that in every cycle we select the samples that are diverse in crowd density and dissimilar to previous selections. In the last cycle when the labeling budget is met, the large amount of unlabeled data are also utilized: a distribution classifier is introduced to align the labeled data with unlabeled data; furthermore, we propose to mix up the distribution labels and latent representations of data in the network to particularly improve the distribution alignment in-between training samples. We follow the popular density estimation pipeline for crowd counting. Extensive experiments are conducted on standard benchmarks i.e. ShanghaiTech, UCF CC 50, MAll, TRANCOS, and DCC. By annotating limited number of images (e.g. 10 of performance not far from the state of the art which utilize full annotations of the dataset.


page 2

page 13

page 17


Completely Self-Supervised Crowd Counting via Distribution Matching

Dense crowd counting is a challenging task that demands millions of head...

Reducing Spatial Labeling Redundancy for Semi-supervised Crowd Counting

Labeling is onerous for crowd counting as it should annotate each indivi...

Leveraging Unlabeled Data for Crowd Counting by Learning to Rank

We propose a novel crowd counting approach that leverages abundantly ava...

S^2FPR: Crowd Counting via Self-Supervised Coarse to Fine Feature Pyramid Ranking

Most conventional crowd counting methods utilize a fully-supervised lear...

Learning to Count in the Crowd from Limited Labeled Data

Recent crowd counting approaches have achieved excellent performance. ho...

Cross-head Supervision for Crowd Counting with Noisy Annotations

Noisy annotations such as missing annotations and location shifts often ...

CrowdNet: A Deep Convolutional Network for Dense Crowd Counting

Our work proposes a novel deep learning framework for estimating crowd d...

Please sign up or login with your details

Forgot password? Click here to reset