# Focus on Semantic Consistency for Cross-domain Crowd Understanding

arXiv: https://arxiv.org/abs/2002.08623 · HTML: https://mlsanity.com/paper/2002.08623/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Feb 2020.

## Built on by (most cited first, 16 of 16)

- [STEERER: Resolving Scale Variations for Counting and Localization via Selective Inheritance Learning](https://mlsanity.com/paper/2308.10468/) (2023)
- [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)
- [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)
- [A Comprehensive Survey on Video Saliency Detection with Auditory Information: the Audio-visual Consistency Perceptual is the Key!](https://mlsanity.com/paper/2206.13390/) (2022)
- [Bi-level Alignment for Cross-Domain Crowd Counting](https://mlsanity.com/paper/2205.05844/) (2022)
- [Semi-supervised Counting via Pixel-by-pixel Density Distribution Modelling](https://mlsanity.com/paper/2402.15297/) (2024)
- [Fine-grained Domain Adaptive Crowd Counting via Point-derived Segmentation](https://mlsanity.com/paper/2108.02980/) (2021)
- [GCNet: Probing Self-Similarity Learning for Generalized Counting Network](https://mlsanity.com/paper/2302.05132/) (2023)
- [Video Individual Counting for Moving Drones](https://mlsanity.com/paper/2503.10701/) (2025)
- [DenseTrack: Drone-based Crowd Tracking via Density-aware Motion-appearance Synergy](https://mlsanity.com/paper/2407.17272/) (2024)
- [Density Map Distillation for Incremental Object Counting](https://mlsanity.com/paper/2304.05255/) (2023)
- [AdaTreeFormer: Few Shot Domain Adaptation for Tree Counting from a Single High-Resolution Image](https://mlsanity.com/paper/2402.02956/) (2024)
- [Count2Density: Crowd Density Estimation without Location-level Annotations](https://mlsanity.com/paper/2509.03170/) (2025)
- [Granular Ball Guided Stable Latent Domain Discovery for Domain-General Crowd Counting](https://mlsanity.com/paper/2603.24106/) (2026)

## Abstract (arXiv)

For pixel-level crowd understanding, it is time-consuming and laborious in data collection and annotation. Some domain adaptation algorithms try to liberate it by training models with synthetic data, and the results in some recent works have proved the feasibility. However, we found that a mass of estimation errors in the background areas impede the performance of the existing methods. In this paper, we propose a domain adaptation method to eliminate it. According to the semantic consistency, a similar distribution in deep layer's features of the synthetic and real-world crowd area, we first introduce a semantic extractor to effectively distinguish crowd and background in high-level semantic information. Besides, to further enhance the adapted model, we adopt adversarial learning to align features in the semantic space. Experiments on three representative real datasets show that the proposed domain adaptation scheme achieves the state-of-the-art for cross-domain counting problems.