论文标题
公正的跨域对象检测的卑鄙老师
Unbiased Mean Teacher for Cross-domain Object Detection
论文作者
论文摘要
跨域对象检测具有挑战性，因为对象检测模型通常容易受到数据差异的影响，尤其是在两个独特的域之间的大量域移动。在本文中，我们为跨域对象检测提出了一个新的无偏见老师（UMT）模型。我们透露，在跨域场景中，通常存在相当大的模型偏见，并以几种简单但高效的策略消除了模型偏见。特别是，对于教师模型，我们提出了一种跨域蒸馏方法，以最大程度地利用教师模型的专业知识。此外，对于学生模型，我们通过使用像素级适应的培训样本来减轻其偏见。最后，对于教学过程，我们采用了分布式估计策略来选择最适合当前模型以进一步增强跨域蒸馏过程的样本。通过解决这些策略的模型偏见问题，我们的UMT模型可在基准数据集clipart1k，withcolor2k，watercolor2k，forgy city scapes和cityscapes上获得44.1％，58.1％，41.7％和43.1％的地图，分别超过了现有的现有状态效果。我们的实施可在https://github.com/kinredon/umt上获得。
Cross-domain object detection is challenging, because object detection model is often vulnerable to data variance, especially to the considerable domain shift between two distinctive domains. In this paper, we propose a new Unbiased Mean Teacher (UMT) model for cross-domain object detection. We reveal that there often exists a considerable model bias for the simple mean teacher (MT) model in cross-domain scenarios, and eliminate the model bias with several simple yet highly effective strategies. In particular, for the teacher model, we propose a cross-domain distillation method for MT to maximally exploit the expertise of the teacher model. Moreover, for the student model, we alleviate its bias by augmenting training samples with pixel-level adaptation. Finally, for the teaching process, we employ an out-of-distribution estimation strategy to select samples that most fit the current model to further enhance the cross-domain distillation process. By tackling the model bias issue with these strategies, our UMT model achieves mAPs of 44.1%, 58.1%, 41.7%, and 43.1% on benchmark datasets Clipart1k, Watercolor2k, Foggy Cityscapes, and Cityscapes, respectively, which outperforms the existing state-of-the-art results in notable margins. Our implementation is available at https://github.com/kinredon/umt.
