# Focus for Free in Density-Based Counting

arXiv: https://arxiv.org/abs/2306.05129 · HTML: https://mlsanity.com/paper/2306.05129/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 99 references that are in the map.
- First posted on arXiv 8 Jun 2023.

## Builds on (most cited first, 30 of 50)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [Computational Optimal Transport](https://mlsanity.com/paper/1803.00567/) (2018)
- [Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation](https://mlsanity.com/paper/2012.07177/) (2020)
- [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](https://mlsanity.com/paper/1802.10062/) (2018)
- [SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning](https://mlsanity.com/paper/1611.05594/) (2016)
- [Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds](https://mlsanity.com/paper/1808.01050/) (2018)
- [Bayesian Loss for Crowd Count Estimation with Point Supervision](https://mlsanity.com/paper/1908.03684/) (2019)
- [Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework](https://mlsanity.com/paper/2107.12746/) (2021)
- [NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization](https://mlsanity.com/paper/2001.03360/) (2020)
- [Context-Aware Crowd Counting](https://mlsanity.com/paper/1811.10452/) (2018)
- [Distribution Matching for Crowd Counting](https://mlsanity.com/paper/2009.13077/) (2020)
- [JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method](https://mlsanity.com/paper/2004.03597/) (2020)
- [Switching Convolutional Neural Network for Crowd Counting](https://mlsanity.com/paper/1708.00199/) (2017)
- [Boosting Crowd Counting via Multifaceted Attention](https://mlsanity.com/paper/2203.02636/) (2022)
- [TransCrowd: weakly-supervised crowd counting with transformers](https://mlsanity.com/paper/2104.09116/) (2021)
- [Leveraging Unlabeled Data for Crowd Counting by Learning to Rank](https://mlsanity.com/paper/1803.03095/) (2018)
- [Crowd Counting and Density Estimation by Trellis Encoder-Decoder Network](https://mlsanity.com/paper/1903.00853/) (2019)
- [Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNs](https://mlsanity.com/paper/1708.00953/) (2017)
- [Perspective-Guided Convolution Networks for Crowd Counting](https://mlsanity.com/paper/1909.06966/) (2019)
- [Rethinking Spatial Invariance of Convolutional Networks for Object Counting](https://mlsanity.com/paper/2206.05253/) (2022)
- [DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimation](https://mlsanity.com/paper/1712.06679/) (2017)
- [Revisiting Perspective Information for Efficient Crowd Counting](https://mlsanity.com/paper/1807.01989/) (2018)
- [Iterative Crowd Counting](https://mlsanity.com/paper/1807.09959/) (2018)
- [ADCrowdNet: An Attention-injective Deformable Convolutional Network for Crowd Understanding](https://mlsanity.com/paper/1811.11968/) (2018)

## Built on by (most cited first, 8 of 8)

- [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)
- [YOLO-Count: Differentiable Object Counting for Text-to-Image Generation](https://mlsanity.com/paper/2508.00728/) (2025)
- [Semi-Supervised Crowd Counting with Contextual Modeling: Facilitating Holistic Understanding of Crowd Scenes](https://mlsanity.com/paper/2310.10352/) (2023)
- [Exploring Scale Shift in Crowd Localization under the Context of Domain Generalization](https://mlsanity.com/paper/2510.19330/) (2025)
- [FSCA-Net: Feature-Separated Cross-Attention Network for Robust Multi-Dataset Training](https://mlsanity.com/paper/2602.01540/) (2026)
- [Thermal-Only Crowd Counting with Deployment-Time Privacy Protection](https://mlsanity.com/paper/2605.17042/) (2026)
- [Object Counting Across Modalities: Taxonomies, Benchmarks, Applications, and Open Challenges](https://mlsanity.com/paper/2608.23845/) (2026)

## Abstract (arXiv)

This work considers supervised learning to count from images and their corresponding point annotations. Where density-based counting methods typically use the point annotations only to create Gaussian-density maps, which act as the supervision signal, the starting point of this work is that point annotations have counting potential beyond density map generation. We introduce two methods that repurpose the available point annotations to enhance counting performance. The first is a counting-specific augmentation that leverages point annotations to simulate occluded objects in both input and density images to enhance the network's robustness to occlusions. The second method, foreground distillation, generates foreground masks from the point annotations, from which we train an auxiliary network on images with blacked-out backgrounds. By doing so, it learns to extract foreground counting knowledge without interference from the background. These methods can be seamlessly integrated with existing counting advances and are adaptable to different loss functions. We demonstrate complementary effects of the approaches, allowing us to achieve robust counting results even in challenging scenarios such as background clutter, occlusion, and varying crowd densities. Our proposed approach achieves strong counting results on multiple datasets, including ShanghaiTech PartA and PartB, UCFQNRF, JHU-Crowd++, and NWPU-Crowd.