arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.06587cs.CV
收藏

隐私保护的目标检测

Privacy-preserving Object Detection

Oxford Artificial Intelligence Society(牛津人工智能学会);University of Oxford(牛津大学)

Peiyang He, Charlie Griffin, Krzysztof Kacprzyk, Artjom Joosen, Michael Collyer, Aleksandar Shtedritski, Yuki M. Asano

摘要:

数据集中的隐私考虑和偏见正在迅速成为计算机视觉社区需要面对的高优先级问题。到目前为止,很少有人注意到不涉及收集新数据集的实际解决方案。在这项工作中,我们表明,对于COCO上的目标检测,通过模糊面部来匿名化数据集,以及沿着性别和肤色维度以平衡的方式交换面部,可以保留目标检测性能,同时保护隐私和部分平衡偏见。

英文摘要:

Privacy considerations and bias in datasets are quickly becoming high-priority issues that the computer vision community needs to face. So far, little attention has been given to practical solutions that do not involve collection of new datasets. In this work, we show that for object detection on COCO, both anonymizing the dataset by blurring faces, as well as swapping faces in a balanced manner along the gender and skin tone dimension, can retain object detection performances while preserving privacy and partially balancing bias.

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。

↑