# Improving the Learning of Multi-column Convolutional Neural Network for Crowd Counting

arXiv: https://arxiv.org/abs/1909.07608 · HTML: https://mlsanity.com/paper/1909.07608/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2019.

## Built on by (most cited first, 15 of 15)

- [Rethinking Spatial Invariance of Convolutional Networks for Object Counting](https://mlsanity.com/paper/2206.05253/) (2022)
- [Training-free Object Counting with Prompts](https://mlsanity.com/paper/2307.00038/) (2023)
- [OmniCount: Multi-label Object Counting with Semantic-Geometric Priors](https://mlsanity.com/paper/2403.05435/) (2024)
- [DAMO-StreamNet: Optimizing Streaming Perception in Autonomous Driving](https://mlsanity.com/paper/2303.17144/) (2023)
- [Crowd Localization from Gaussian Mixture Scoped Knowledge and Scoped Teacher](https://mlsanity.com/paper/2206.05717/) (2022)
- [PoSynDA: Multi-Hypothesis Pose Synthesis Domain Adaptation for Robust 3D Human Pose Estimation](https://mlsanity.com/paper/2308.09678/) (2023)
- [Focus for Free in Density-Based Counting](https://mlsanity.com/paper/2306.05129/) (2023)
- [FGENet: Fine-Grained Extraction Network for Congested Crowd Counting](https://mlsanity.com/paper/2401.01208/) (2024)
- [Multi-View People Detection in Large Scenes via Supervised View-Wise Contribution Weighting](https://mlsanity.com/paper/2405.19943/) (2024)
- [Robust Zero-Shot Crowd Counting and Localization With Adaptive Resolution SAM](https://mlsanity.com/paper/2402.17514/) (2024)
- [KeyPosS: Plug-and-Play Facial Landmark Detection through GPS-Inspired True-Range Multilateration](https://mlsanity.com/paper/2305.16437/) (2023)
- [POPoS: Improving Efficient and Robust Facial Landmark Detection with Parallel Optimal Position Search](https://mlsanity.com/paper/2410.09583/) (2024)
- [Enhanced Information Fusion Network for Crowd Counting](https://mlsanity.com/paper/2101.04279/) (2021)
- [PANet: Perspective-Aware Network with Dynamic Receptive Fields and Self-Distilling Supervision for Crowd Counting](https://mlsanity.com/paper/2111.00406/) (2021)
- [SynMVCrowd: A Large Synthetic Benchmark for Multi-view Crowd Counting and Localization](https://mlsanity.com/paper/2603.23956/) (2026)

## Abstract (arXiv)

Tremendous variation in the scale of people/head size is a critical problem for crowd counting. To improve the scale invariance of feature representation, recent works extensively employ Convolutional Neural Networks with multi-column structures to handle different scales and resolutions. However, due to the substantial redundant parameters in columns, existing multi-column networks invariably exhibit almost the same scale features in different columns, which severely affects counting accuracy and leads to overfitting. In this paper, we attack this problem by proposing a novel Multi-column Mutual Learning (McML) strategy. It has two main innovations: 1) A statistical network is incorporated into the multi-column framework to estimate the mutual information between columns, which can approximately indicate the scale correlation between features from different columns. By minimizing the mutual information, each column is guided to learn features with different image scales. 2) We devise a mutual learning scheme that can alternately optimize each column while keeping the other columns fixed on each mini-batch training data. With such asynchronous parameter update process, each column is inclined to learn different feature representation from others, which can efficiently reduce the parameter redundancy and improve generalization ability. More remarkably, McML can be applied to all existing multi-column networks and is end-to-end trainable. Extensive experiments on four challenging benchmarks show that McML can significantly improve the original multi-column networks and outperform the other state-of-the-art approaches.