# Divide and Grow: Capturing Huge Diversity in Crowd Images with Incrementally Growing CNN

arXiv: https://arxiv.org/abs/1807.09993 · HTML: https://mlsanity.com/paper/1807.09993/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jul 2018.

## Built on by (most cited first, 19 of 19)

- [Learning To Count Everything](https://mlsanity.com/paper/2104.08391/) (2021)
- [Exemplar Free Class Agnostic Counting](https://mlsanity.com/paper/2205.14212/) (2022)
- [Leveraging Self-Supervision for Cross-Domain Crowd Counting](https://mlsanity.com/paper/2103.16291/) (2021)
- [Redesigning Multi-Scale Neural Network for Crowd Counting](https://mlsanity.com/paper/2208.02894/) (2022)
- [Coarse to Fine: Domain Adaptive Crowd Counting via Adversarial Scoring Network](https://mlsanity.com/paper/2107.12858/) (2021)
- [Rethinking Global Context in Crowd Counting](https://mlsanity.com/paper/2105.10926/) (2021)
- [Focus for Free in Density-Based Counting](https://mlsanity.com/paper/2306.05129/) (2023)
- [Crowd counting with crowd attention convolutional neural network](https://mlsanity.com/paper/2204.07347/) (2022)
- [Towards More Effective PRM-based Crowd Counting via A Multi-resolution Fusion and Attention Network](https://mlsanity.com/paper/2112.09664/) (2021)
- [BBA-net: A bi-branch attention network for crowd counting](https://mlsanity.com/paper/2201.08983/) (2022)
- [Counting with Adaptive Auxiliary Learning](https://mlsanity.com/paper/2203.04061/) (2022)
- [SSR-HEF: Crowd Counting with Multi-Scale Semantic Refining and Hard Example Focusing](https://mlsanity.com/paper/2204.07406/) (2022)
- [Multi-channel Deep Supervision for Crowd Counting](https://mlsanity.com/paper/2103.09553/) (2021)
- [PANet: Perspective-Aware Network with Dynamic Receptive Fields and Self-Distilling Supervision for Crowd Counting](https://mlsanity.com/paper/2111.00406/) (2021)
- [Crowd counting with segmentation attention convolutional neural network](https://mlsanity.com/paper/2204.07380/) (2022)
- [Inception-Based Crowd Counting -- Being Fast while Remaining Accurate](https://mlsanity.com/paper/2210.09796/) (2022)
- [Enhancing Mobile Face Anti-Spoofing: A Robust Framework for Diverse Attack Types under Screen Flash](https://mlsanity.com/paper/2308.15346/) (2023)
- [One-Shot Crowd Counting With Density Guidance For Scene Adaptation](https://mlsanity.com/paper/2602.07955/) (2026)
- [SynMVCrowd: A Large Synthetic Benchmark for Multi-view Crowd Counting and Localization](https://mlsanity.com/paper/2603.23956/) (2026)

## Abstract (arXiv)

Automated counting of people in crowd images is a challenging task. The major difficulty stems from the large diversity in the way people appear in crowds. In fact, features available for crowd discrimination largely depend on the crowd density to the extent that people are only seen as blobs in a highly dense scene. We tackle this problem with a growing CNN which can progressively increase its capacity to account for the wide variability seen in crowd scenes. Our model starts from a base CNN density regressor, which is trained in equivalence on all types of crowd images. In order to adapt with the huge diversity, we create two child regressors which are exact copies of the base CNN. A differential training procedure divides the dataset into two clusters and fine-tunes the child networks on their respective specialties. Consequently, without any hand-crafted criteria for forming specialties, the child regressors become experts on certain types of crowds. The child networks are again split recursively, creating two experts at every division. This hierarchical training leads to a CNN tree, where the child regressors are more fine experts than any of their parents. The leaf nodes are taken as the final experts and a classifier network is then trained to predict the correct specialty for a given test image patch. The proposed model achieves higher count accuracy on major crowd datasets. Further, we analyse the characteristics of specialties mined automatically by our method.