arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.00595cs.CV
收藏

Box Re-Ranking:无监督误报抑制的领域自适应行人检测

Box Re-Ranking: Unsupervised False Positive Suppression for Domain Adaptive Pedestrian Detection

Zhejiang University(浙江大学);Hikvision Research Institute(海康威视研究院)

Weijie Chen, Yilu Guo, Shicai Yang, Zhaoyang Li, Zhenxin Ma, Binbin Chen, Long Zhao, Di Xie, Shiliang Pu, Yueting Zhuang

摘要:

在领域自适应行人检测中,不可知的领域移动带来的最严重的问题之一是误报。然而,不可能在无数的目标域中标记每个框。因此,它引起了我们的注意,以无监督的方式抑制每个目标域中的误报。本文创新性地将目标检测任务建模为正负盒排序任务,从而将误报抑制问题巧妙地转化为盒重排序问题,使得无需人工标注即可求解。在框重新排序过程中出现的附加问题是,没有标记的验证数据可用于cherrypicking。考虑到我们的目标是保持真阳性的检测不变,我们提出了框号对齐,一个自监督的评价指标,以防止优化模型的容量退化。在跨域行人检测数据集上进行的大量实验证明了我们提出的框架的有效性。此外,扩展到两个一般的无监督域自适应目标检测基准也支持我们的优势,其他国家的最先进的。

英文摘要:

False positive is one of the most serious problems brought by agnostic domain shift in domain adaptive pedestrian detection. However, it is impossible to label each box in countless target domains. Therefore, it yields our attention to suppress false positive in each target domain in an unsupervised way. In this paper, we model an object detection task into a ranking task among positive and negative boxes innovatively, and thus transform a false positive suppression problem into a box re-ranking problem elegantly, which makes it feasible to solve without manual annotation. An attached problem during box re-ranking appears that no labeled validation data is available for cherrypicking. Considering we aim to keep the detection of true positive unchanged, we propose box number alignment, a self-supervised evaluation metric, to prevent the optimized model from capacity degeneration. Extensive experiments conducted on cross-domain pedestrian detection datasets have demonstrated the effectiveness of our proposed framework. Furthermore, the extension to two general unsupervised domain adaptive object detection benchmarks also supports our superiority to other state-of-the-arts.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑