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

Abstract

Labeled crowd scene images are expensive and scarce. To significantly reduce the requirement of the labeled images, we propose ColorCount, a novel CNN-based approach by combining self-supervised transfer colorization learning and global prior classification to leverage the abundantly available unlabeled data. The self-supervised colorization branch learns the semantics and surface texture of the image by using its color components as pseudo labels. The classification branch extracts global group priors by learning correlations among image clusters. Their fused resultant discriminative features (global priors, semantics and textures) provide ample priors for counting, hence significantly reducing the requirement of labeled images. We conduct extensive experiments on four challenging benchmarks. ColorCount achieves much better performance as compared with other unsupervised approaches. Its performance is close to the supervised baseline with substantially less labeled data (10\% of the original one).

References in corpus (5)

• A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation
• Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank
• Crowd Counting by Adaptively Fusing Predictions from an Image Pyramid
• Spatiotemporal Dilated Convolution with Uncertain Matching for Video-based Crowd Estimation
• Motion-guided Non-local Spatial-Temporal Network for Video Crowd Counting