# Leveraging Self-Supervision for Cross-Domain Crowd Counting

arXiv: https://arxiv.org/abs/2103.16291 · HTML: https://mlsanity.com/paper/2103.16291/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 78 of its 115 references that are in the map.
- First posted on arXiv 30 Mar 2021.

## Builds on (most cited first, 30 of 78)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1811.12833/) (2018)
- [Deep Transfer Learning with Joint Adaptation Networks](https://mlsanity.com/paper/1605.06636/) (2016)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [Confidence Regularized Self-Training](https://mlsanity.com/paper/1908.09822/) (2019)
- [Contrastive Adaptation Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1901.00976/) (2019)
- [DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion](https://mlsanity.com/paper/1901.04780/) (2019)
- [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](https://mlsanity.com/paper/1802.10062/) (2018)
- [FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation](https://mlsanity.com/paper/1612.02649/) (2016)
- [Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1903.04064/) (2019)
- [Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning](https://mlsanity.com/paper/2002.06470/) (2020)
- [Simultaneous Deep Transfer Across Domains and Tasks](https://mlsanity.com/paper/1510.02192/) (2015)
- [Domain-Specific Batch Normalization for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1906.03950/) (2019)
- [Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds](https://mlsanity.com/paper/1808.01050/) (2018)
- [Generate To Adapt: Aligning Domains using Generative Adversarial Networks](https://mlsanity.com/paper/1704.01705/) (2017)
- [Progressive Feature Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1811.08585/) (2018)
- [Bayesian Loss for Crowd Count Estimation with Point Supervision](https://mlsanity.com/paper/1908.03684/) (2019)
- [Context-Aware Crowd Counting](https://mlsanity.com/paper/1811.10452/) (2018)
- [Learning from Synthetic Data for Crowd Counting in the Wild](https://mlsanity.com/paper/1903.03303/) (2019)
- [Transferrable Prototypical Networks for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1904.11227/) (2019)
- [Gradually Vanishing Bridge for Adversarial Domain Adaptation](https://mlsanity.com/paper/2003.13183/) (2020)
- [Domain-Symmetric Networks for Adversarial Domain Adaptation](https://mlsanity.com/paper/1904.04663/) (2019)

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

- [Zero-shot Object Counting](https://mlsanity.com/paper/2303.02001/) (2023)
- [Improving Point-based Crowd Counting and Localization Based on Auxiliary Point Guidance](https://mlsanity.com/paper/2405.10589/) (2024)
- [Domain-General Crowd Counting in Unseen Scenarios](https://mlsanity.com/paper/2212.02573/) (2022)
- [Reconstructing Groups of People with Hypergraph Relational Reasoning](https://mlsanity.com/paper/2308.15844/) (2023)
- [DEBOSH: Deep Bayesian Shape Optimization](https://mlsanity.com/paper/2109.13337/) (2021)
- [Counting Crowds in Bad Weather](https://mlsanity.com/paper/2306.01209/) (2023)
- [DAOT: Domain-Agnostically Aligned Optimal Transport for Domain-Adaptive Crowd Counting](https://mlsanity.com/paper/2308.05311/) (2023)
- [CountFormer: Multi-View Crowd Counting Transformer](https://mlsanity.com/paper/2407.02047/) (2024)
- [Coarse to Fine: Domain Adaptive Crowd Counting via Adversarial Scoring Network](https://mlsanity.com/paper/2107.12858/) (2021)
- [Forget Less, Count Better: A Domain-Incremental Self-Distillation Learning Benchmark for Lifelong Crowd Counting](https://mlsanity.com/paper/2205.03307/) (2022)
- [RGB-D Indiscernible Object Counting in Underwater Scenes](https://mlsanity.com/paper/2304.11677/) (2023)
- [Zero-Shot Object Counting with Language-Vision Models](https://mlsanity.com/paper/2309.13097/) (2023)
- [Counting Stacked Objects](https://mlsanity.com/paper/2411.19149/) (2024)
- [Semi-supervised Counting via Pixel-by-pixel Density Distribution Modelling](https://mlsanity.com/paper/2402.15297/) (2024)
- [Video Individual Counting for Moving Drones](https://mlsanity.com/paper/2503.10701/) (2025)
- [Supervision Interpolation via LossMix: Generalizing Mixup for Object Detection and Beyond](https://mlsanity.com/paper/2303.10343/) (2023)
- [Object counting from aerial remote sensing images: application to wildlife and marine mammals](https://mlsanity.com/paper/2306.10439/) (2023)
- [Dynamic Proxy Domain Generalizes the Crowd Localization by Better Binary Segmentation](https://mlsanity.com/paper/2404.13992/) (2024)
- [Face Density as a Proxy for Data Complexity: Quantifying the Hardness of Instance Count](https://mlsanity.com/paper/2604.09689/) (2026)
- [L2HCount:Generalizing Crowd Counting from Low to High Crowd Density via Density Simulation](https://mlsanity.com/paper/2503.12935/) (2025)
- [Automated Counting of Stacked Objects in Industrial Inspection](https://mlsanity.com/paper/2603.15470/) (2026)
- [Learning from Pseudo-labeled Segmentation for Multi-Class Object Counting](https://mlsanity.com/paper/2307.07677/) (2023)
- [Transformer-Based Dual-Optical Attention Fusion Crowd Head Point Counting and Localization Network](https://mlsanity.com/paper/2505.06937/) (2025)
- [Count2Density: Crowd Density Estimation without Location-level Annotations](https://mlsanity.com/paper/2509.03170/) (2025)

## Abstract (arXiv)

State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density. While effective, these data-driven approaches rely on large amount of data annotation to achieve good performance, which stops these models from being deployed in emergencies during which data annotation is either too costly or cannot be obtained fast enough. One popular solution is to use synthetic data for training. Unfortunately, due to domain shift, the resulting models generalize poorly on real imagery. We remedy this shortcoming by training with both synthetic images, along with their associated labels, and unlabeled real images. To this end, we force our network to learn perspective-aware features by training it to recognize upside-down real images from regular ones and incorporate into it the ability to predict its own uncertainty so that it can generate useful pseudo labels for fine-tuning purposes. This yields an algorithm that consistently outperforms state-of-the-art cross-domain crowd counting ones without any extra computation at inference time.