TL;DR提出一种基于不对称三路 Faster-RCNN 和辅助网络的非监督域自适应目标检测方法,在保证安全性的同时提高了区别性并在多个数据集上达到 SOTA 性能。
Abstract
Conventional object detection models inevitably encounter a performance drop
as the domain disparity exists. unsupervised domain adaptive object detection
is proposed recently to reduce the disparity between domains, where the source
domain is label-rich while the target domain is labe