Cross domain object detection is challenging, because object detection model is often vulnerable to data variance, especially to the considerable domain shift in cross domain scenarios. In this paper, we propose a new approach called Unbiased Mean Teacher (UMT) for cross domain object detection. While the simple mean teacher (MT) model exhibits good robustness to small data variance, it can also become easily biased in cross domain scenarios. We thus improve it with several simple yet highly effective strategies. In particular, we firstly propose a novel cross domain distillation for MT to maximally exploit the expertise of the teacher model. Then, we further alleviate the bias in the student model by augmenting training samples with pixel-level adaptation. The feature level adversarial training is also incorporated to learn domain-invariant representation. Those strategies can be implemented easily into MT and leads to our unbiased MT model. Our model surpasses the existing state-of-the-art models in large margins on benchmark datasets, which demonstrates the effectiveness of our approach.

本研究提出了一种新的UMT模型，通过消除教师模型的偏差、使用像素级别的自适应增强训练样本、以及采用基于分布的估算策略来选择最适合当前模型的样本，从而消除了跨域识别中常见的模型偏差，并取得了显著的性能提升。

基于无偏均衡学习的跨领域目标检测方法