# Bi-level Alignment for Cross-Domain Crowd Counting

arXiv: https://arxiv.org/abs/2205.05844 · HTML: https://mlsanity.com/paper/2205.05844/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 34 references that are in the map.
- First posted on arXiv 12 May 2022.

## Builds on (most cited first, 25 of 25)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [Progressive Neural Architecture Search](https://mlsanity.com/paper/1712.00559/) (2017)
- [A Fourier-based Framework for Domain Generalization](https://mlsanity.com/paper/2105.11120/) (2021)
- [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](https://mlsanity.com/paper/1802.10062/) (2018)
- [Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data](https://mlsanity.com/paper/1909.00889/) (2019)
- [Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds](https://mlsanity.com/paper/1808.01050/) (2018)
- [Neural Architecture Optimization](https://mlsanity.com/paper/1808.07233/) (2018)
- [FSDR: Frequency Space Domain Randomization for Domain Generalization](https://mlsanity.com/paper/2103.02370/) (2021)
- [Learning from Synthetic Data for Crowd Counting in the Wild](https://mlsanity.com/paper/1903.03303/) (2019)
- [AutoGAN: Neural Architecture Search for Generative Adversarial Networks](https://mlsanity.com/paper/1908.03835/) (2019)
- [LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search](https://mlsanity.com/paper/2104.14545/) (2021)
- [NAS-Count: Counting-by-Density with Neural Architecture Search](https://mlsanity.com/paper/2003.00217/) (2020)
- [PCC Net: Perspective Crowd Counting via Spatial Convolutional Network](https://mlsanity.com/paper/1905.10085/) (2019)
- [Learning to Count in the Crowd from Limited Labeled Data](https://mlsanity.com/paper/2007.03195/) (2020)
- [Pixel-wise Crowd Understanding via Synthetic Data](https://mlsanity.com/paper/2007.16032/) (2020)
- [Focus on Semantic Consistency for Cross-domain Crowd Understanding](https://mlsanity.com/paper/2002.08623/) (2020)
- [One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking](https://mlsanity.com/paper/2104.00597/) (2021)
- [CODA: Counting Objects via Scale-aware Adversarial Density Adaption](https://mlsanity.com/paper/1903.10442/) (2019)
- [AutoHAS: Efficient Hyperparameter and Architecture Search](https://mlsanity.com/paper/2006.03656/) (2020)
- [Inverse Attention Guided Deep Crowd Counting Network](https://mlsanity.com/paper/1907.01193/) (2019)

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

- [Domain-General Crowd Counting in Unseen Scenarios](https://mlsanity.com/paper/2212.02573/) (2022)
- [DAOT: Domain-Agnostically Aligned Optimal Transport for Domain-Adaptive Crowd Counting](https://mlsanity.com/paper/2308.05311/) (2023)
- [A First-order Generative Bilevel Optimization Framework for Diffusion Models](https://mlsanity.com/paper/2502.08808/) (2025)
- [Virtual Classification: Modulating Domain-Specific Knowledge for Multidomain Crowd Counting](https://mlsanity.com/paper/2402.03758/) (2024)
- [L2HCount:Generalizing Crowd Counting from Low to High Crowd Density via Density Simulation](https://mlsanity.com/paper/2503.12935/) (2025)
- [Exploring Scale Shift in Crowd Localization under the Context of Domain Generalization](https://mlsanity.com/paper/2510.19330/) (2025)
- [Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods](https://mlsanity.com/paper/2601.12500/) (2026)
- [Count2Density: Crowd Density Estimation without Location-level Annotations](https://mlsanity.com/paper/2509.03170/) (2025)

## Abstract (arXiv)

Recently, crowd density estimation has received increasing attention. The main challenge for this task is to achieve high-quality manual annotations on a large amount of training data. To avoid reliance on such annotations, previous works apply unsupervised domain adaptation (UDA) techniques by transferring knowledge learned from easily accessible synthetic data to real-world datasets. However, current state-of-the-art methods either rely on external data for training an auxiliary task or apply an expensive coarse-to-fine estimation. In this work, we aim to develop a new adversarial learning based method, which is simple and efficient to apply. To reduce the domain gap between the synthetic and real data, we design a bi-level alignment framework (BLA) consisting of (1) task-driven data alignment and (2) fine-grained feature alignment. In contrast to previous domain augmentation methods, we introduce AutoML to search for an optimal transform on source, which well serves for the downstream task. On the other hand, we do fine-grained alignment for foreground and background separately to alleviate the alignment difficulty. We evaluate our approach on five real-world crowd counting benchmarks, where we outperform existing approaches by a large margin. Also, our approach is simple, easy to implement and efficient to apply. The code is publicly available at https://github.com/Yankeegsj/BLA.