Multi-channel Deep Supervision for Crowd Counting
Not on the map. Why?
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 32 of its 55 references that are in the map. First posted on arXiv 17 Mar 2021.
Builds on
32 of 55 references.
References · 32
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2017Squeeze-and-Excitation Networkscited by 4,763
- 2014Going Deeper with Convolutionscited by 4,231
- 2016Pyramid Scene Parsing Networkcited by 2,472
- 2015Holistically-Nested Edge Detectioncited by 590
- 2014Deeply-Supervised Netscited by 364
- 2018CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenescited by 267
- 2019Bayesian Loss for Crowd Count Estimation with Point Supervisioncited by 162
- 2020NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localizationcited by 151
- 2018Context-Aware Crowd Countingcited by 150
- 2019Learning from Synthetic Data for Crowd Counting in the Wildcited by 148
- 2017Switching Convolutional Neural Network for Crowd Countingcited by 93
20 more
- 2017Repulsion Loss: Detecting Pedestrians in a Crowdcited by 62
- 2018Leveraging Unlabeled Data for Crowd Counting by Learning to Rankcited by 57
- 2019Crowd Counting and Density Estimation by Trellis Encoder-Decoder Networkcited by 56
- 2017Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNscited by 55
- 2016CrowdNet: A Deep Convolutional Network for Dense Crowd Countingcited by 52
- 2017DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimationcited by 49
- 2017CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Countingcited by 41
- 2019PCC Net: Perspective Crowd Counting via Spatial Convolutional Networkcited by 33
- 2017A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimationcited by 29
- 2020Pixel-wise Crowd Understanding via Synthetic Datacited by 23
- 2018Crowd Counting using Deep Recurrent Spatial-Aware Networkcited by 21
- 2018Object Detection from Scratch with Deep Supervisioncited by 21
- 2020Hybrid Graph Neural Networks for Crowd Countingcited by 21
- 2019Crowd Counting with Decomposed Uncertaintycited by 20
- 2020Active Crowd Counting with Limited Supervisioncited by 20
- 2016Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsingcited by 19
- 2018Deep Supervision with Intermediate Conceptscited by 19
- 2018Divide and Grow: Capturing Huge Diversity in Crowd Images with Incrementally Growing CNNcited by 19
- 2018Top-Down Feedback for Crowd Counting Convolutional Neural Networkcited by 14
- 2016Crowd Counting by Adapting Convolutional Neural Networks with Side Informationcited by 2
Built on by
Not cited yet.