# Weighing Counts: Sequential Crowd Counting by Reinforcement Learning

arXiv: https://arxiv.org/abs/2007.08260 · HTML: https://mlsanity.com/paper/2007.08260/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jul 2020.

## Built on by (most cited first, 30 of 30)

- [Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework](https://mlsanity.com/paper/2107.12746/) (2021)
- [Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting](https://mlsanity.com/paper/2203.08354/) (2022)
- [An End-to-End Transformer Model for Crowd Localization](https://mlsanity.com/paper/2202.13065/) (2022)
- [TransCrowd: weakly-supervised crowd counting with transformers](https://mlsanity.com/paper/2104.09116/) (2021)
- [Rethinking Spatial Invariance of Convolutional Networks for Object Counting](https://mlsanity.com/paper/2206.05253/) (2022)
- [Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey](https://mlsanity.com/paper/2108.11510/) (2021)
- [Point-Query Quadtree for Crowd Counting, Localization, and More](https://mlsanity.com/paper/2308.13814/) (2023)
- [Focal Inverse Distance Transform Maps for Crowd Localization](https://mlsanity.com/paper/2102.07925/) (2021)
- [CCTrans: Simplifying and Improving Crowd Counting with Transformer](https://mlsanity.com/paper/2109.14483/) (2021)
- [Calibrating Uncertainty for Semi-Supervised Crowd Counting](https://mlsanity.com/paper/2308.09887/) (2023)
- [Improving Point-based Crowd Counting and Localization Based on Auxiliary Point Guidance](https://mlsanity.com/paper/2405.10589/) (2024)
- [Uniformity in Heterogeneity:Diving Deep into Count Interval Partition for Crowd Counting](https://mlsanity.com/paper/2107.12619/) (2021)
- [CrowdDiff: Multi-hypothesis Crowd Density Estimation using Diffusion Models](https://mlsanity.com/paper/2303.12790/) (2023)
- [Revisiting Crowd Counting: State-of-the-art, Trends, and Future Perspectives](https://mlsanity.com/paper/2209.07271/) (2022)
- [Crowd Counting via Perspective-Guided Fractional-Dilation Convolution](https://mlsanity.com/paper/2107.03665/) (2021)
- [Video Crowd Localization with Multi-focus Gaussian Neighborhood Attention and a Large-Scale Benchmark](https://mlsanity.com/paper/2107.08645/) (2021)
- [Scene-Adaptive Attention Network for Crowd Counting](https://mlsanity.com/paper/2112.15509/) (2021)
- [CountFormer: Multi-View Crowd Counting Transformer](https://mlsanity.com/paper/2407.02047/) (2024)
- [Rethinking Global Context in Crowd Counting](https://mlsanity.com/paper/2105.10926/) (2021)
- [CrowdFormer: Weakly-supervised Crowd counting with Improved Generalizability](https://mlsanity.com/paper/2203.03768/) (2022)
- [Counting Varying Density Crowds Through Density Guided Adaptive Selection CNN and Transformer Estimation](https://mlsanity.com/paper/2206.10075/) (2022)
- [Cross-head Supervision for Crowd Counting with Noisy Annotations](https://mlsanity.com/paper/2303.09245/) (2023)
- [Fine-grained Domain Adaptive Crowd Counting via Point-derived Segmentation](https://mlsanity.com/paper/2108.02980/) (2021)
- [Hybrid attention network based on progressive embedding scale-context for crowd counting](https://mlsanity.com/paper/2106.02324/) (2021)
- [Reinforcement Learning for Adaptive Video Compressive Sensing](https://mlsanity.com/paper/2105.08205/) (2021)
- [Multi-scale Feature Aggregation for Crowd Counting](https://mlsanity.com/paper/2208.05256/) (2022)
- [Reducing Spatial Labeling Redundancy for Semi-supervised Crowd Counting](https://mlsanity.com/paper/2108.02970/) (2021)
- [Indirect-Instant Attention Optimization for Crowd Counting in Dense Scenes](https://mlsanity.com/paper/2206.05648/) (2022)
- [HDNet: A Hierarchically Decoupled Network for Crowd Counting](https://mlsanity.com/paper/2212.05722/) (2022)
- [Crowd Counting with Sparse Annotation](https://mlsanity.com/paper/2304.06021/) (2023)

## Abstract (arXiv)

We formulate counting as a sequential decision problem and present a novel crowd counting model solvable by deep reinforcement learning. In contrast to existing counting models that directly output count values, we divide one-step estimation into a sequence of much easier and more tractable sub-decision problems. Such sequential decision nature corresponds exactly to a physical process in reality scale weighing. Inspired by scale weighing, we propose a novel 'counting scale' termed LibraNet where the count value is analogized by weight. By virtually placing a crowd image on one side of a scale, LibraNet (agent) sequentially learns to place appropriate weights on the other side to match the crowd count. At each step, LibraNet chooses one weight (action) from the weight box (the pre-defined action pool) according to the current crowd image features and weights placed on the scale pan (state). LibraNet is required to learn to balance the scale according to the feedback of the needle (Q values). We show that LibraNet exactly implements scale weighing by visualizing the decision process how LibraNet chooses actions. Extensive experiments demonstrate the effectiveness of our design choices and report state-of-the-art results on a few crowd counting benchmarks. We also demonstrate good cross-dataset generalization of LibraNet. Code and models are made available at: https://git.io/libranet