# Learning Independent Instance Maps for Crowd Localization

arXiv: https://arxiv.org/abs/2012.04164 · HTML: https://mlsanity.com/paper/2012.04164/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Dec 2020.

## Built on by (most cited first, 24 of 24)

- [An End-to-End Transformer Model for Crowd Localization](https://mlsanity.com/paper/2202.13065/) (2022)
- [STEERER: Resolving Scale Variations for Counting and Localization via Selective Inheritance Learning](https://mlsanity.com/paper/2308.10468/) (2023)
- [Focal Inverse Distance Transform Maps for Crowd Localization](https://mlsanity.com/paper/2102.07925/) (2021)
- [Improving Point-based Crowd Counting and Localization Based on Auxiliary Point Guidance](https://mlsanity.com/paper/2405.10589/) (2024)
- [DR.VIC: Decomposition and Reasoning for Video Individual Counting](https://mlsanity.com/paper/2203.12335/) (2022)
- [Counting Crowds in Bad Weather](https://mlsanity.com/paper/2306.01209/) (2023)
- [Boosting Detection in Crowd Analysis via Underutilized Output Features](https://mlsanity.com/paper/2308.16187/) (2023)
- [Audio-visual Representation Learning for Anomaly Events Detection in Crowds](https://mlsanity.com/paper/2110.14862/) (2021)
- [Crowd Localization from Gaussian Mixture Scoped Knowledge and Scoped Teacher](https://mlsanity.com/paper/2206.05717/) (2022)
- [Congested Crowd Instance Localization with Dilated Convolutional Swin Transformer](https://mlsanity.com/paper/2108.00584/) (2021)
- [Counting Varying Density Crowds Through Density Guided Adaptive Selection CNN and Transformer Estimation](https://mlsanity.com/paper/2206.10075/) (2022)
- [Consistency-Aware Anchor Pyramid Network for Crowd Localization](https://mlsanity.com/paper/2212.04067/) (2022)
- [Learning Discriminative Features for Crowd Counting](https://mlsanity.com/paper/2311.04509/) (2023)
- [Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting](https://mlsanity.com/paper/2505.21943/) (2025)
- [LDC-Net: A Unified Framework for Localization, Detection and Counting in Dense Crowds](https://mlsanity.com/paper/2110.04727/) (2021)
- [Counting Like Human: Anthropoid Crowd Counting on Modeling the Similarity of Objects](https://mlsanity.com/paper/2212.02248/) (2022)
- [Few-shot Object Localization](https://mlsanity.com/paper/2403.12466/) (2024)
- [Dynamic Proxy Domain Generalizes the Crowd Localization by Better Binary Segmentation](https://mlsanity.com/paper/2404.13992/) (2024)
- [Tree Counting by Bridging 3D Point Clouds with Imagery](https://mlsanity.com/paper/2403.01932/) (2024)
- [Exploring Scale Shift in Crowd Localization under the Context of Domain Generalization](https://mlsanity.com/paper/2510.19330/) (2025)
- [Text-guided Zero-Shot Object Localization](https://mlsanity.com/paper/2411.11357/) (2024)
- [Crowd Detection Using Very-Fine-Resolution Satellite Imagery](https://mlsanity.com/paper/2504.19546/) (2025)
- [Transformer-Based Dual-Optical Attention Fusion Crowd Head Point Counting and Localization Network](https://mlsanity.com/paper/2505.06937/) (2025)
- [DenseControl: Instance-Level Controllable Synthesis of Dense Crowd Image](https://mlsanity.com/paper/2606.15592/) (2026)

## Abstract (arXiv)

Accurately locating each head's position in the crowd scenes is a crucial task in the field of crowd analysis. However, traditional density-based methods only predict coarse prediction, and segmentation/detection-based methods cannot handle extremely dense scenes and large-range scale-variations crowds. To this end, we propose an end-to-end and straightforward framework for crowd localization, named Independent Instance Map segmentation (IIM). Different from density maps and boxes regression, each instance in IIM is non-overlapped. By segmenting crowds into independent connected components, the positions and the crowd counts (the centers and the number of components, respectively) are obtained. Furthermore, to improve the segmentation quality for different density regions, we present a differentiable Binarization Module (BM) to output structured instance maps. BM brings two advantages into localization models: 1) adaptively learn a threshold map for different images to detect each instance more accurately; 2) directly train the model using loss on binary predictions and labels. Extensive experiments verify the proposed method is effective and outperforms the-state-of-the-art methods on the five popular crowd datasets. Significantly, IIM improves F1-measure by 10.4% on the NWPU-Crowd Localization task. The source code and pre-trained models will be released at https://github.com/taohan10200/IIM.