# Top-Down Feedback for Crowd Counting Convolutional Neural Network

arXiv: https://arxiv.org/abs/1807.08881 · HTML: https://mlsanity.com/paper/1807.08881/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jul 2018.

## Built on by (most cited first, 14 of 14)

- [Few-shot Object Counting with Similarity-Aware Feature Enhancement](https://mlsanity.com/paper/2201.08959/) (2022)
- [FBNet: Feedback Network for Point Cloud Completion](https://mlsanity.com/paper/2210.03974/) (2022)
- [Glance to Count: Learning to Rank with Anchors for Weakly-supervised Crowd Counting](https://mlsanity.com/paper/2205.14659/) (2022)
- [Crowd counting with crowd attention convolutional neural network](https://mlsanity.com/paper/2204.07347/) (2022)
- [Multi-Level Attentive Convoluntional Neural Network for Crowd Counting](https://mlsanity.com/paper/2105.11422/) (2021)
- [Multi-scale Feature Aggregation for Crowd Counting](https://mlsanity.com/paper/2208.05256/) (2022)
- [Iterative Feedback Network for Unsupervised Point Cloud Registration](https://mlsanity.com/paper/2401.04357/) (2024)
- [Power Battery Detection](https://mlsanity.com/paper/2508.07797/) (2025)
- [Multi-channel Deep Supervision for Crowd Counting](https://mlsanity.com/paper/2103.09553/) (2021)
- [Visual Sensation and Perception Computational Models for Deep Learning: State of the art, Challenges and Prospects](https://mlsanity.com/paper/2109.03391/) (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)
- [A Lightweight Feature Fusion Architecture For Resource-Constrained Crowd Counting](https://mlsanity.com/paper/2401.05968/) (2024)
- [Real-Time Crowd Counting for Embedded Systems with Lightweight Architecture](https://mlsanity.com/paper/2510.13250/) (2025)

## Abstract (arXiv)

Counting people in dense crowds is a demanding task even for humans. This is primarily due to the large variability in appearance of people. Often people are only seen as a bunch of blobs. Occlusions, pose variations and background clutter further compound the difficulty. In this scenario, identifying a person requires larger spatial context and semantics of the scene. But the current state-of-the-art CNN regressors for crowd counting are feedforward and use only limited spatial context to detect people. They look for local crowd patterns to regress the crowd density map, resulting in false predictions. Hence, we propose top-down feedback to correct the initial prediction of the CNN. Our architecture consists of a bottom-up CNN along with a separate top-down CNN to generate feedback. The bottom-up network, which regresses the crowd density map, has two columns of CNN with different receptive fields. Features from various layers of the bottom-up CNN are fed to the top-down network. The feedback, thus generated, is applied on the lower layers of the bottom-up network in the form of multiplicative gating. This masking weighs activations of the bottom-up network at spatial as well as feature levels to correct the density prediction. We evaluate the performance of our model on all major crowd datasets and show the effectiveness of top-down feedback.