# Towards Domain Generalization in Object Detection

arXiv: https://arxiv.org/abs/2203.14387 · HTML: https://mlsanity.com/paper/2203.14387/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 79 of its 104 references that are in the map.
- First posted on arXiv 27 Mar 2022.

## Builds on (most cited first, 30 of 79)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [CornerNet: Detecting Objects as Paired Keypoints](https://mlsanity.com/paper/1808.01244/) (2018)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [Sim-to-Real Transfer of Robotic Control with Dynamics Randomization](https://mlsanity.com/paper/1710.06537/) (2017)
- [CenterNet: Keypoint Triplets for Object Detection](https://mlsanity.com/paper/1904.08189/) (2019)
- [Domain Generalization via Invariant Feature Representation](https://mlsanity.com/paper/1301.2115/) (2013)
- [Training Region-based Object Detectors with Online Hard Example Mining](https://mlsanity.com/paper/1604.03540/) (2016)
- [Object Detection in 20 Years: A Survey](https://mlsanity.com/paper/1905.05055/) (2019)
- [Generalizing to Unseen Domains via Adversarial Data Augmentation](https://mlsanity.com/paper/1805.12018/) (2018)

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

- [Model Agnostic Sample Reweighting for Out-of-Distribution Learning](https://mlsanity.com/paper/2301.09819/) (2023)
- [COCO-O: A Benchmark for Object Detectors under Natural Distribution Shifts](https://mlsanity.com/paper/2307.12730/) (2023)
- [MDT3D: Multi-Dataset Training for LiDAR 3D Object Detection Generalization](https://mlsanity.com/paper/2308.01000/) (2023)
- [Normalization Perturbation: A Simple Domain Generalization Method for Real-World Domain Shifts](https://mlsanity.com/paper/2211.04393/) (2022)
- [Persistent Homology Meets Object Unity: Object Recognition in Clutter](https://mlsanity.com/paper/2305.03815/) (2023)
- [Domain-invariant Progressive Knowledge Distillation for UAV-based Object Detection](https://mlsanity.com/paper/2408.11407/) (2024)
- [Street Gaussians without 3D Object Tracker](https://mlsanity.com/paper/2412.05548/) (2024)
- [Pareto Invariant Representation Learning for Multimedia Recommendation](https://mlsanity.com/paper/2308.04706/) (2023)
- [Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies](https://mlsanity.com/paper/2505.22829/) (2025)
- [Decoupled Mixup for Generalized Visual Recognition](https://mlsanity.com/paper/2210.14783/) (2022)
- [ScAR: Scaling Adversarial Robustness for LiDAR Object Detection](https://mlsanity.com/paper/2312.03085/) (2023)
- [Cross-domain Transfer of defect features in technical domains based on partial target data](https://mlsanity.com/paper/2211.13662/) (2022)
- [Generalizable Person Search on Open-world User-Generated Video Content](https://mlsanity.com/paper/2310.10068/) (2023)
- [Seeking Flat Minima with Mean Teacher on Semi- and Weakly-Supervised Domain Generalization for Object Detection](https://mlsanity.com/paper/2310.19351/) (2023)
- [Improving Generalization Performance of YOLOv8 for Camera Trap Object Detection](https://mlsanity.com/paper/2412.14211/) (2024)
- [CornerPoint3D: Look at the Nearest Corner Instead of the Center](https://mlsanity.com/paper/2504.02464/) (2025)

## Abstract (arXiv)

Despite the striking performance achieved by modern detectors when training and test data are sampled from the same or similar distribution, the generalization ability of detectors under unknown distribution shifts remains hardly studied. Recently several works discussed the detectors' adaptation ability to a specific target domain which are not readily applicable in real-world applications since detectors may encounter various environments or situations while pre-collecting all of them before training is inconceivable. In this paper, we study the critical problem, domain generalization in object detection (DGOD), where detectors are trained with source domains and evaluated on unknown target domains. To thoroughly evaluate detectors under unknown distribution shifts, we formulate the DGOD problem and propose a comprehensive evaluation benchmark to fill the vacancy. Moreover, we propose a novel method named Region Aware Proposal reweighTing (RAPT) to eliminate dependence within RoI features. Extensive experiments demonstrate that current DG methods fail to address the DGOD problem and our method outperforms other state-of-the-art counterparts.