Multi-channel Deep Supervision for Crowd Counting

TL;DR

This paper introduces MDSNet, a novel crowd counting network utilizing multi-channel deep supervision and an auxiliary network to improve accuracy by addressing overfitting and detail loss, achieving competitive results.

Contribution

The paper proposes MDSNet with a new multi-channel deep supervision framework and an auxiliary SupervisionNet to enhance crowd counting accuracy without altering the base network structure.

Findings

MDSNet achieves competitive results on mainstream benchmarks.

Multi-channel deep supervision significantly improves performance.

The approach effectively handles overfitting and detail loss issues.

Abstract

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.