论文标题
使用SE适配器和中心损失的域适应以进行对象检测
Domain Adaptation for Object Detection using SE Adaptors and Center Loss
论文作者
论文摘要
尽管对物体检测的兴趣日益增加，但很少有作品解决了跨域鲁棒性极为实用的问题，尤其是对于自动化应用而言。为了防止由于域移动而导致的性能下降，我们引入了一种无监督的域适应方法，建立在更快的RCNN基础上，其中有两个域的适应组件分别解决了实例和图像级别上的变化，并在它们之间应用一致性正则化。我们还介绍了一个适应层的家族，该层利用称为SE适配器的挤压激发机制来提高域的注意力，从而提高性能，而无需任何知识对新目标域的了解。最后，我们在实例和图像级表示中纳入了中心损失，以改善类内的方差。我们将城市景观的所有结果报告为我们的来源领域和有雾的城市景观，因为目标域优于先前的基线。
Despite growing interest in object detection, very few works address the extremely practical problem of cross-domain robustness especially for automative applications. In order to prevent drops in performance due to domain shift, we introduce an unsupervised domain adaptation method built on the foundation of faster-RCNN with two domain adaptation components addressing the shift at the instance and image levels respectively and apply a consistency regularization between them. We also introduce a family of adaptation layers that leverage the squeeze excitation mechanism called SE Adaptors to improve domain attention and thus improves performance without any prior requirement of knowledge of the new target domain. Finally, we incorporate a center loss in the instance and image level representations to improve the intra-class variance. We report all results with Cityscapes as our source domain and Foggy Cityscapes as the target domain outperforming previous baselines.
