NinjaDesc: Content-Concealing Visual Descriptors via Adversarial Learning

Citations Over TimeTop 12% of 2022 papers

Abstract

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.

Related Papers

• → Performance Comparison of Three Types of Autoencoder Neural Networks(2008)28 cited
• → The difference learning of hidden layer between autoencoder and variational autoencoder(2017)26 cited
• → The Learning Effect of Different Hidden Layers Stacked Autoencoder(2016)20 cited
• → Combining an Autoencoder and a Variational Autoencoder for Explaining the Machine Learning Model Predictions(2021)5 cited
• → A Comparative Evaluation of AutoEncoder-Based Unsupervised Anomaly Detection Methods Applied on Space Payload(2020)