# Reducing Spatial Labeling Redundancy for Semi-supervised Crowd Counting

arXiv: https://arxiv.org/abs/2108.02970 · HTML: https://mlsanity.com/paper/2108.02970/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 49 references that are in the map.
- First posted on arXiv 6 Aug 2021.

## Builds on (most cited first, 24 of 24)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (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)
- [Bayesian Loss for Crowd Count Estimation with Point Supervision](https://mlsanity.com/paper/1908.03684/) (2019)
- [Context-Aware Crowd Counting](https://mlsanity.com/paper/1811.10452/) (2018)
- [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)
- [Crowd Counting and Density Estimation by Trellis Encoder-Decoder Network](https://mlsanity.com/paper/1903.00853/) (2019)
- [Perspective-Guided Convolution Networks for Crowd Counting](https://mlsanity.com/paper/1909.06966/) (2019)
- [Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank](https://mlsanity.com/paper/1902.06285/) (2019)
- [Revisiting Perspective Information for Efficient Crowd Counting](https://mlsanity.com/paper/1807.01989/) (2018)
- [ADCrowdNet: An Attention-injective Deformable Convolutional Network for Crowd Understanding](https://mlsanity.com/paper/1811.11968/) (2018)
- [CNN-based Density Estimation and Crowd Counting: A Survey](https://mlsanity.com/paper/2003.12783/) (2020)
- [Semi-Supervised Crowd Counting via Self-Training on Surrogate Tasks](https://mlsanity.com/paper/2007.03207/) (2020)
- [HA-CCN: Hierarchical Attention-based Crowd Counting Network](https://mlsanity.com/paper/1907.10255/) (2019)
- [Weighing Counts: Sequential Crowd Counting by Reinforcement Learning](https://mlsanity.com/paper/2007.08260/) (2020)
- [Shallow Feature Based Dense Attention Network for Crowd Counting](https://mlsanity.com/paper/2006.09853/) (2020)
- [Learning to Count in the Crowd from Limited Labeled Data](https://mlsanity.com/paper/2007.03195/) (2020)
- [Crowded Scene Analysis: A Survey](https://mlsanity.com/paper/1502.01812/) (2015)
- [Hybrid Graph Neural Networks for Crowd Counting](https://mlsanity.com/paper/2002.00092/) (2020)
- [Crowd Counting with Decomposed Uncertainty](https://mlsanity.com/paper/1903.07427/) (2019)
- [Active Crowd Counting with Limited Supervision](https://mlsanity.com/paper/2007.06334/) (2020)
- [Uncertainty Estimation and Sample Selection for Crowd Counting](https://mlsanity.com/paper/2009.14411/) (2020)

## Abstract (arXiv)

Labeling is onerous for crowd counting as it should annotate each individual in crowd images. Recently, several methods have been proposed for semi-supervised crowd counting to reduce the labeling efforts. Given a limited labeling budget, they typically select a few crowd images and densely label all individuals in each of them. Despite the promising results, we argue the None-or-All labeling strategy is suboptimal as the densely labeled individuals in each crowd image usually appear similar while the massive unlabeled crowd images may contain entirely diverse individuals. To this end, we propose to break the labeling chain of previous methods and make the first attempt to reduce spatial labeling redundancy for semi-supervised crowd counting. First, instead of annotating all the regions in each crowd image, we propose to annotate the representative ones only. We analyze the region representativeness from both vertical and horizontal directions, and formulate them as cluster centers of Gaussian Mixture Models. Additionally, to leverage the rich unlabeled regions, we exploit the similarities among individuals in each crowd image to directly supervise the unlabeled regions via feature propagation instead of the error-prone label propagation employed in the previous methods. In this way, we can transfer the original spatial labeling redundancy caused by individual similarities to effective supervision signals on the unlabeled regions. Extensive experiments on the widely-used benchmarks demonstrate that our method can outperform previous best approaches by a large margin.