# Universal Domain Adaptive Object Detection via Dual Probabilistic Alignment

arXiv: https://arxiv.org/abs/2412.11443 · HTML: https://mlsanity.com/paper/2412.11443/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 44 references that are in the map.
- First posted on arXiv 16 Dec 2024.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [Semantic Foggy Scene Understanding with Synthetic Data](https://mlsanity.com/paper/1708.07819/) (2017)
- [Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation](https://mlsanity.com/paper/1803.11365/) (2018)
- [Universal Domain Adaptation through Self Supervision](https://mlsanity.com/paper/2002.07953/) (2020)
- [Harmonizing Transferability and Discriminability for Adapting Object Detectors](https://mlsanity.com/paper/2003.06297/) (2020)
- [Multi-adversarial Faster-RCNN for Unrestricted Object Detection](https://mlsanity.com/paper/1907.10343/) (2019)
- [Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector](https://mlsanity.com/paper/2008.08574/) (2020)
- [Importance Weighted Adversarial Nets for Partial Domain Adaptation](https://mlsanity.com/paper/1803.09210/) (2018)
- [SIGMA: Semantic-complete Graph Matching for Domain Adaptive Object Detection](https://mlsanity.com/paper/2203.06398/) (2022)
- [Learning Domain Adaptive Object Detection with Probabilistic Teacher](https://mlsanity.com/paper/2206.06293/) (2022)
- [Unified Optimal Transport Framework for Universal Domain Adaptation](https://mlsanity.com/paper/2210.17067/) (2022)
- [Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers](https://mlsanity.com/paper/2107.12636/) (2021)
- [Towards Robust Adaptive Object Detection under Noisy Annotations](https://mlsanity.com/paper/2204.02620/) (2022)
- [MLNet: Mutual Learning Network with Neighborhood Invariance for Universal Domain Adaptation](https://mlsanity.com/paper/2312.07871/) (2023)
- [MILA: Memory-Based Instance-Level Adaptation for Cross-Domain Object Detection](https://mlsanity.com/paper/2309.01086/) (2023)
- [Predicting Class Distribution Shift for Reliable Domain Adaptive Object Detection](https://mlsanity.com/paper/2302.06039/) (2023)
- [BlenDA: Domain Adaptive Object Detection through diffusion-based blending](https://mlsanity.com/paper/2401.09921/) (2024)

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

- [Generalization Under Scrutiny: Cross-Domain Detection Progresses, Pitfalls, and Persistent Challenges](https://mlsanity.com/paper/2604.08230/) (2026)
- [Joint Distribution Alignment for Universal Domain Adaptation](https://mlsanity.com/paper/2608.24429/) (2026)

## Abstract (arXiv)

Domain Adaptive Object Detection (DAOD) transfers knowledge from a labeled source domain to an unannotated target domain under closed-set assumption. Universal DAOD (UniDAOD) extends DAOD to handle open-set, partial-set, and closed-set domain adaptation. In this paper, we first unveil two issues: domain-private category alignment is crucial for global-level features, and the domain probability heterogeneity of features across different levels. To address these issues, we propose a novel Dual Probabilistic Alignment (DPA) framework to model domain probability as Gaussian distribution, enabling the heterogeneity domain distribution sampling and measurement. The DPA consists of three tailored modules: the Global-level Domain Private Alignment (GDPA), the Instance-level Domain Shared Alignment (IDSA), and the Private Class Constraint (PCC). GDPA utilizes the global-level sampling to mine domain-private category samples and calculate alignment weight through a cumulative distribution function to address the global-level private category alignment. IDSA utilizes instance-level sampling to mine domain-shared category samples and calculates alignment weight through Gaussian distribution to conduct the domain-shared category domain alignment to address the feature heterogeneity. The PCC aggregates domain-private category centroids between feature and probability spaces to mitigate negative transfer. Extensive experiments demonstrate that our DPA outperforms state-of-the-art UniDAOD and DAOD methods across various datasets and scenarios, including open, partial, and closed sets. Codes are available at urlhttps://github.com/zyfone/DPA.