This paper presents a Simple and effective unsupervised adaptation method for Robust Object Detection (SimROD). To overcome the challenging issues of domain shift and pseudo-label noise, our method integrates a novel domain-centric augmentation method, a gradual self-labeling adaptation procedure, and a teacher-guided fine-tuning mechanism. Using our method, target domain samples can be leveraged to adapt object detection models without changing the model architecture or generating synthetic data. When applied to image corruptions and high-level cross-domain adaptation benchmarks, our method outperforms prior baselines on multiple domain adaptation benchmarks. SimROD achieves new state-of-the-art on standard real-to-synthetic and cross-camera setup benchmarks. On the image corruption benchmark, models adapted with our method achieved a relative robustness improvement of 15-25% AP50 on Pascal-C and 5-6% AP on COCO-C and Cityscapes-C. On the cross-domain benchmark, our method outperformed the best baseline performance by up to 8% AP50 on Comic dataset and up to 4% on Watercolor dataset.

中文翻译：

---

SimROD：一种用于鲁棒对象检测的简单自适应方法

本文提出了一种简单有效的无监督自适应方法，用于鲁棒对象检测（SimROD）。为了克服域转移和伪标签噪声的挑战性问题，我们的方法集成了一种新的以域为中心的增强方法、一个渐进的自标记适应程序和一个教师指导的微调机制。使用我们的方法，可以利用目标域样本来调整对象检测模型，而无需更改模型架构或生成合成数据。当应用于图像损坏和高级跨域自适应基准测试时，我们的方法在多个域自适应基准测试中优于先前的基准。SimROD 在标准的真实到合成和跨相机设置基准上实现了最新的最新技术。在图像损坏基准上，采用我们方法的模型在 Pascal-C 上实现了 15-25% AP50 的相对稳健性改进，在 COCO-C 和 Cityscapes-C 上实现了 5-6% AP 的相对稳健性改进。在跨域基准测试中，我们的方法在 Comic 数据集上比最佳基线性能高出 8% AP50，在 Watercolor 数据集上高出 4%。