Privacy-Preserving Deep Visual Recognition: An Adversarial Learning Framework and A New Dataset

12 Jun 2019Haotao WangZhenyu WuZhangyang WangZhaowen WangHailin Jin

This paper aims to boost privacy-preserving visual recognition, an increasingly demanded feature in smart camera applications, using deep learning. We formulate a unique adversarial training framework, that learns a degradation transform for the original video inputs, in order to explicitly optimize the trade-off between target task performance and the associated privacy budgets on the degraded video... (read more)

PDF Abstract

Evaluation results from the paper


  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.