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

arXiv: https://arxiv.org/abs/2105.09684 · HTML: https://mlsanity.com/paper/2105.09684/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 41 references that are in the map.
- First posted on arXiv 20 May 2021.

## Builds on (most cited first, 19 of 19)

- [Colorful Image Colorization](https://mlsanity.com/paper/1603.08511/) (2016)
- [Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/1902.06162/) (2019)
- [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](https://mlsanity.com/paper/1802.10062/) (2018)
- [Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds](https://mlsanity.com/paper/1808.01050/) (2018)
- [Learning from Synthetic Data for Crowd Counting in the Wild](https://mlsanity.com/paper/1903.03303/) (2019)
- [Real-Time User-Guided Image Colorization with Learned Deep Priors](https://mlsanity.com/paper/1705.02999/) (2017)
- [Switching Convolutional Neural Network for Crowd Counting](https://mlsanity.com/paper/1708.00199/) (2017)
- [Leveraging Unlabeled Data for Crowd Counting by Learning to Rank](https://mlsanity.com/paper/1803.03095/) (2018)
- [Perspective-Guided Convolution Networks for Crowd Counting](https://mlsanity.com/paper/1909.06966/) (2019)
- [CrowdNet: A Deep Convolutional Network for Dense Crowd Counting](https://mlsanity.com/paper/1608.06197/) (2016)
- [Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank](https://mlsanity.com/paper/1902.06285/) (2019)
- [DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimation](https://mlsanity.com/paper/1712.06679/) (2017)
- [A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation](https://mlsanity.com/paper/1707.01202/) (2017)
- [Crowd Counting using Deep Recurrent Spatial-Aware Network](https://mlsanity.com/paper/1807.00601/) (2018)
- [Crowd Counting by Adaptively Fusing Predictions from an Image Pyramid](https://mlsanity.com/paper/1805.06115/) (2018)
- [Spatiotemporal Dilated Convolution with Uncertain Matching for Video-based Crowd Estimation](https://mlsanity.com/paper/2101.12439/) (2021)
- [Crowd Counting on Images with Scale Variation and Isolated Clusters](https://mlsanity.com/paper/1909.03839/) (2019)
- [Multi-Scale Attention Network for Crowd Counting](https://mlsanity.com/paper/1901.06026/) (2019)
- [Motion-guided Non-local Spatial-Temporal Network for Video Crowd Counting](https://mlsanity.com/paper/2104.13946/) (2021)

## Abstract (arXiv)

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).