# DAOT: Domain-Agnostically Aligned Optimal Transport for Domain-Adaptive Crowd Counting arXiv: https://arxiv.org/abs/2308.05311 ยท HTML: https://mlsanity.com/paper/2308.05311/ ## Key facts - Cited by 12 papers in the map (data through 14 Oct 2026). - Builds on 29 of its 55 references that are in the map. - First posted on arXiv 10 Aug 2023. ## Builds on (most cited first, 29 of 29) - [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014) - [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013) - [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019) - [Computational Optimal Transport](https://mlsanity.com/paper/1803.00567/) (2018) - [Image Matching across Wide Baselines: From Paper to Practice](https://mlsanity.com/paper/2003.01587/) (2020) - [DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1803.10081/) (2018) - [Statistical Aspects of Wasserstein Distances](https://mlsanity.com/paper/1806.05500/) (2018) - [Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds](https://mlsanity.com/paper/1808.01050/) (2018) - [Trusted Multi-View Classification with Dynamic Evidential Fusion](https://mlsanity.com/paper/2204.11423/) (2022) - [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) - [Learning from Synthetic Data for Crowd Counting in the Wild](https://mlsanity.com/paper/1903.03303/) (2019) - [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) - [Boosting Crowd Counting via Multifaceted Attention](https://mlsanity.com/paper/2203.02636/) (2022) - [Focal Inverse Distance Transform Maps for Crowd Localization](https://mlsanity.com/paper/2102.07925/) (2021) - [Learn to Scale: Generating Multipolar Normalized Density Maps for Crowd Counting](https://mlsanity.com/paper/1907.12428/) (2019) - [Domain-adaptive Crowd Counting via High-quality Image Translation and Density Reconstruction](https://mlsanity.com/paper/1912.03677/) (2019) - [Leveraging Self-Supervision for Cross-Domain Crowd Counting](https://mlsanity.com/paper/2103.16291/) (2021) - [Domain-General Crowd Counting in Unseen Scenarios](https://mlsanity.com/paper/2212.02573/) (2022) - [DR.VIC: Decomposition and Reasoning for Video Individual Counting](https://mlsanity.com/paper/2203.12335/) (2022) - [Crowd Counting via Perspective-Guided Fractional-Dilation Convolution](https://mlsanity.com/paper/2107.03665/) (2021) - [Towards Unsupervised Crowd Counting via Regression-Detection Bi-knowledge Transfer](https://mlsanity.com/paper/2008.05383/) (2020) - [CODA: Counting Objects via Scale-aware Adversarial Density Adaption](https://mlsanity.com/paper/1903.10442/) (2019) - [Coarse to Fine: Domain Adaptive Crowd Counting via Adversarial Scoring Network](https://mlsanity.com/paper/2107.12858/) (2021) - [Spatiotemporal Dilated Convolution with Uncertain Matching for Video-based Crowd Estimation](https://mlsanity.com/paper/2101.12439/) (2021) - [Bi-level Alignment for Cross-Domain Crowd Counting](https://mlsanity.com/paper/2205.05844/) (2022) - [Fine-grained Domain Adaptive Crowd Counting via Point-derived Segmentation](https://mlsanity.com/paper/2108.02980/) (2021) ## Built on by (most cited first, 12 of 12) - [Zero-shot Object Counting with Good Exemplars](https://mlsanity.com/paper/2407.04948/) (2024) - [Single Domain Generalization for Crowd Counting](https://mlsanity.com/paper/2403.09124/) (2024) - [CountFormer: Multi-View Crowd Counting Transformer](https://mlsanity.com/paper/2407.02047/) (2024) - [Single Domain Generalization for Few-Shot Counting via Universal Representation Matching](https://mlsanity.com/paper/2505.16778/) (2025) - [Taste More, Taste Better: Diverse Data and Strong Model Boost Semi-Supervised Crowd Counting](https://mlsanity.com/paper/2503.17984/) (2025) - [DenseTrack: Drone-based Crowd Tracking via Density-aware Motion-appearance Synergy](https://mlsanity.com/paper/2407.17272/) (2024) - [Dynamic Proxy Domain Generalizes the Crowd Localization by Better Binary Segmentation](https://mlsanity.com/paper/2404.13992/) (2024) - [Exploring Scale Shift in Crowd Localization under the Context of Domain Generalization](https://mlsanity.com/paper/2510.19330/) (2025) - [Towards Conditional Feature Alignment for Cross-Domain Counting](https://mlsanity.com/paper/2506.17137/) (2025) - [Reducing Domain Gap with Diffusion-Based Domain Adaptation for Cell Counting](https://mlsanity.com/paper/2512.11763/) (2025) - [One-Shot Crowd Counting With Density Guidance For Scene Adaptation](https://mlsanity.com/paper/2602.07955/) (2026) - [Granular Ball Guided Stable Latent Domain Discovery for Domain-General Crowd Counting](https://mlsanity.com/paper/2603.24106/) (2026) ## Abstract (arXiv) Domain adaptation is commonly employed in crowd counting to bridge the domain gaps between different datasets. However, existing domain adaptation methods tend to focus on inter-dataset differences while overlooking the intra-differences within the same dataset, leading to additional learning ambiguities. These domain-agnostic factors, e.g., density, surveillance perspective, and scale, can cause significant in-domain variations, and the misalignment of these factors across domains can lead to a drop in performance in cross-domain crowd counting. To address this issue, we propose a Domain-agnostically Aligned Optimal Transport (DAOT) strategy that aligns domain-agnostic factors between domains. The DAOT consists of three steps. First, individual-level differences in domain-agnostic factors are measured using structural similarity (SSIM). Second, the optimal transfer (OT) strategy is employed to smooth out these differences and find the optimal domain-to-domain misalignment, with outlier individuals removed via a virtual "dustbin" column. Third, knowledge is transferred based on the aligned domain-agnostic factors, and the model is retrained for domain adaptation to bridge the gap across domains. We conduct extensive experiments on five standard crowd-counting benchmarks and demonstrate that the proposed method has strong generalizability across diverse datasets. Our code will be available at: https://github.com/HopooLinZ/DAOT/.