# MVUDA: Unsupervised Domain Adaptation for Multi-view Pedestrian Detection

arXiv: https://arxiv.org/abs/2412.04117 · HTML: https://mlsanity.com/paper/2412.04117/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 51 references that are in the map.
- First posted on arXiv 5 Dec 2024.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2111.14887/) (2021)
- [FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation](https://mlsanity.com/paper/1612.02649/) (2016)
- [Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2003.03773/) (2020)
- [DLOW: Domain Flow for Adaptation and Generalization](https://mlsanity.com/paper/1812.05418/) (2018)
- [Unbiased Mean Teacher for Cross-domain Object Detection](https://mlsanity.com/paper/2003.00707/) (2020)
- [Exploring Object Relation in Mean Teacher for Cross-Domain Detection](https://mlsanity.com/paper/1904.11245/) (2019)
- [MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking](https://mlsanity.com/paper/1504.01942/) (2015)
- [Cross-Domain Adaptive Teacher for Object Detection](https://mlsanity.com/paper/2111.13216/) (2021)
- [Multiview Detection with Feature Perspective Transformation](https://mlsanity.com/paper/2007.07247/) (2020)
- [Contrastive Mean Teacher for Domain Adaptive Object Detectors](https://mlsanity.com/paper/2305.03034/) (2023)
- [Multiview Detection with Shadow Transformer (and View-Coherent Data Augmentation)](https://mlsanity.com/paper/2108.05888/) (2021)
- [Deep Occlusion Reasoning for Multi-Camera Multi-Target Detection](https://mlsanity.com/paper/1704.05775/) (2017)
- [Deep Multi-camera People Detection](https://mlsanity.com/paper/1702.04593/) (2017)
- [EarlyBird: Early-Fusion for Multi-View Tracking in the Bird's Eye View](https://mlsanity.com/paper/2310.13350/) (2023)
- [3D Random Occlusion and Multi-Layer Projection for Deep Multi-Camera Pedestrian Localization](https://mlsanity.com/paper/2207.10895/) (2022)
- [Two-level Data Augmentation for Calibrated Multi-view Detection](https://mlsanity.com/paper/2210.10756/) (2022)
- [Bringing Generalization to Deep Multi-View Pedestrian Detection](https://mlsanity.com/paper/2109.12227/) (2021)
- [Semantic Driven Multi-Camera Pedestrian Detection](https://mlsanity.com/paper/1812.10779/) (2018)
- [Toward unlabeled multi-view 3D pedestrian detection by generalizable AI: techniques and performance analysis](https://mlsanity.com/paper/2308.04515/) (2023)

## Built on by (most cited first, 2 of 2)

- [DCHM: Depth-Consistent Human Modeling for Multiview Detection](https://mlsanity.com/paper/2507.14505/) (2025)
- [CAT-Free: Multi-View Pedestrian Localization without Calibration, Annotations, or Target-Scene Training via Adaptive Geometric Filtering](https://mlsanity.com/paper/2609.34302/) (2026)

## Abstract (arXiv)

We address multi-view pedestrian detection in a setting where labeled data is collected using a multi-camera setup different from the one used for testing. While recent multi-view pedestrian detectors perform well on the camera rig used for training, their performance declines when applied to a different setup. To facilitate seamless deployment across varied camera rigs, we propose an unsupervised domain adaptation (UDA) method that adapts the model to new rigs without requiring additional labeled data. Specifically, we leverage the mean teacher self-training framework with a novel pseudo-labeling technique tailored to multi-view pedestrian detection. This method achieves state-of-the-art performance on multiple benchmarks, including MultiviewXrightarrowWildtrack. Unlike previous methods, our approach eliminates the need for external labeled monocular datasets, thereby reducing reliance on labeled data. Extensive evaluations demonstrate the effectiveness of our method and validate key design choices. By enabling robust adaptation across camera setups, our work enhances the practicality of multi-view pedestrian detectors and establishes a strong UDA baseline for future research.