S4-Crowd: Semi-Supervised Learning with Self-Supervised Regularisation for Crowd Counting

08/31/2021
by   Haoran Duan, et al.
0

Crowd counting has drawn more attention because of its wide application in smart cities. Recent works achieved promising performance but relied on the supervised paradigm with expensive crowd annotations. To alleviate annotation cost, in this work we proposed a semi-supervised learning framework S4-Crowd, which can leverage both unlabeled/labeled data for robust crowd modelling. In the unsupervised pathway, two self-supervised losses were proposed to simulate the crowd variations such as scale, illumination, etc., based on which and the supervised information pseudo labels were generated and gradually refined. We also proposed a crowd-driven recurrent unit Gated-Crowd-Recurrent-Unit (GCRU), which can preserve discriminant crowd information by extracting second-order statistics, yielding pseudo labels with improved quality. A joint loss including both unsupervised/supervised information was proposed, and a dynamic weighting strategy was employed to balance the importance of the unsupervised loss and supervised loss at different training stages. We conducted extensive experiments on four popular crowd counting datasets in semi-supervised settings. Experimental results suggested the effectiveness of each proposed component in our S4-Crowd framework. Our method also outperformed other state-of-the-art semi-supervised learning approaches on these crowd datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/07/2020

Semi-Supervised Crowd Counting via Self-Training on Surrogate Tasks

Most existing crowd counting systems rely on the availability of the obj...
research
08/09/2020

SOFA-Net: Second-Order and First-order Attention Network for Crowd Counting

Automated crowd counting from images/videos has attracted more attention...
research
05/20/2021

Crowd Counting by Self-supervised Transfer Colorization Learning and Global Prior Classification

Labeled crowd scene images are expensive and scarce. To significantly re...
research
10/27/2021

International Workshop on Continual Semi-Supervised Learning: Introduction, Benchmarks and Baselines

The aim of this paper is to formalize a new continual semi-supervised le...
research
07/28/2021

Spatial Uncertainty-Aware Semi-Supervised Crowd Counting

Semi-supervised approaches for crowd counting attract attention, as the ...
research
08/12/2020

Towards Unsupervised Crowd Counting via Regression-Detection Bi-knowledge Transfer

Unsupervised crowd counting is a challenging yet not largely explored ta...
research
08/06/2021

Reducing Spatial Labeling Redundancy for Semi-supervised Crowd Counting

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

Please sign up or login with your details

Forgot password? Click here to reset