NinjaDesc: Content-Concealing Visual Descriptors via Adversarial Learning
This addresses privacy concerns for users of visual recognition systems, though it is an incremental improvement in adversarial learning for descriptor security.
The paper tackles the problem of privacy leakage from visual descriptors by developing descriptors that conceal image content while maintaining matching accuracy, achieving significant deterioration in image reconstruction quality with minimal impact on matching and camera localization.
In the light of recent analyses on privacy-concerning scene revelation from visual descriptors, we develop descriptors that conceal the input image content. In particular, we propose an adversarial learning framework for training visual descriptors that prevent image reconstruction, while maintaining the matching accuracy. We let a feature encoding network and image reconstruction network compete with each other, such that the feature encoder tries to impede the image reconstruction with its generated descriptors, while the reconstructor tries to recover the input image from the descriptors. The experimental results demonstrate that the visual descriptors obtained with our method significantly deteriorate the image reconstruction quality with minimal impact on correspondence matching and camera localization performance.