# Multi-channel Deep Supervision for Crowd Counting

arXiv: https://arxiv.org/abs/2103.09553 · HTML: https://mlsanity.com/paper/2103.09553/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 55 references that are in the map.
- First posted on arXiv 17 Mar 2021.

## Builds on (most cited first, 30 of 32)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [Deeply-Supervised Nets](https://mlsanity.com/paper/1409.5185/) (2014)
- [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](https://mlsanity.com/paper/1802.10062/) (2018)
- [Bayesian Loss for Crowd Count Estimation with Point Supervision](https://mlsanity.com/paper/1908.03684/) (2019)
- [NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization](https://mlsanity.com/paper/2001.03360/) (2020)
- [Context-Aware Crowd Counting](https://mlsanity.com/paper/1811.10452/) (2018)
- [Learning from Synthetic Data for Crowd Counting in the Wild](https://mlsanity.com/paper/1903.03303/) (2019)
- [Switching Convolutional Neural Network for Crowd Counting](https://mlsanity.com/paper/1708.00199/) (2017)
- [Repulsion Loss: Detecting Pedestrians in a Crowd](https://mlsanity.com/paper/1711.07752/) (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)
- [Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNs](https://mlsanity.com/paper/1708.00953/) (2017)
- [CrowdNet: A Deep Convolutional Network for Dense Crowd Counting](https://mlsanity.com/paper/1608.06197/) (2016)
- [DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimation](https://mlsanity.com/paper/1712.06679/) (2017)
- [CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting](https://mlsanity.com/paper/1707.09605/) (2017)
- [PCC Net: Perspective Crowd Counting via Spatial Convolutional Network](https://mlsanity.com/paper/1905.10085/) (2019)
- [A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation](https://mlsanity.com/paper/1707.01202/) (2017)
- [Pixel-wise Crowd Understanding via Synthetic Data](https://mlsanity.com/paper/2007.16032/) (2020)
- [Crowd Counting using Deep Recurrent Spatial-Aware Network](https://mlsanity.com/paper/1807.00601/) (2018)
- [Object Detection from Scratch with Deep Supervision](https://mlsanity.com/paper/1809.09294/) (2018)
- [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)
- [Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing](https://mlsanity.com/paper/1612.02699/) (2016)
- [Deep Supervision with Intermediate Concepts](https://mlsanity.com/paper/1801.03399/) (2018)
- [Divide and Grow: Capturing Huge Diversity in Crowd Images with Incrementally Growing CNN](https://mlsanity.com/paper/1807.09993/) (2018)

## Abstract (arXiv)

Crowd counting is a task worth exploring in modern society because of its wide applications such as public safety and video monitoring. Many CNN-based approaches have been proposed to improve the accuracy of estimation, but there are some inherent issues affect the performance, such as overfitting and details lost caused by pooling layers. To tackle these problems, in this paper, we propose an effective network called MDSNet, which introduces a novel supervision framework called Multi-channel Deep Supervision (MDS). The MDS conducts channel-wise supervision on the decoder of the estimation model to help generate the density maps. To obtain the accurate supervision information of different channels, the MDSNet employs an auxiliary network called SupervisionNet (SN) to generate abundant supervision maps based on existing groundtruth. Besides the traditional density map supervision, we also use the SN to convert the dot annotations into continuous supervision information and conduct dot supervision in the MDSNet. Extensive experiments on several mainstream benchmarks show that the proposed MDSNet achieves competitive results and the MDS significantly improves the performance without changing the network structure.