论文标题
使用偏移到边界框的一阶段对象检测器的无监督域改编
Unsupervised Domain Adaptation for One-stage Object Detector using Offsets to Bounding Box
论文作者
论文摘要
大多数现有的域自适应对象检测方法利用对抗性特征对齐，以使模型适应新域。对抗性特征比对的最新进展旨在减少发生的负面影响或负转移的负面影响，因为特征的分布取决于对象类别。但是，通过分析无锚的一阶段检测器的特征，在本文中，我们发现可能发生负转移，因为特征分布取决于对边界框的回归值以及类别的回归值而变化。为了通过解决此问题来获得域的不变性，我们考虑了特征分布的模态，以偏移值为条件。通过一种非常简单有效的调节方法，我们提出了在各种实验环境中实现最先进的性能的OADA（偏移感知域自适应对象检测器）。此外，通过通过单数值分解分析，我们发现我们的模型增强了可区分性和可传递性。
Most existing domain adaptive object detection methods exploit adversarial feature alignment to adapt the model to a new domain. Recent advances in adversarial feature alignment strives to reduce the negative effect of alignment, or negative transfer, that occurs because the distribution of features varies depending on the category of objects. However, by analyzing the features of the anchor-free one-stage detector, in this paper, we find that negative transfer may occur because the feature distribution varies depending on the regression value for the offset to the bounding box as well as the category. To obtain domain invariance by addressing this issue, we align the feature conditioned on the offset value, considering the modality of the feature distribution. With a very simple and effective conditioning method, we propose OADA (Offset-Aware Domain Adaptive object detector) that achieves state-of-the-art performances in various experimental settings. In addition, by analyzing through singular value decomposition, we find that our model enhances both discriminability and transferability.
