Generative Model Adversarial Training for Deep Compressed Sensing
This work addresses robustness in compressed sensing for applications like imaging or signal processing, but it appears incremental as it builds on existing deep compressed sensing methods.
The paper tackles the problem of designing a robust low-to-high-dimensional generator for deep compressed sensing that is resilient to universal adversarial perturbations in the latent space, with results supported by theoretical analysis and experiments on real-world datasets.
Deep compressed sensing assumes the data has sparse representation in a latent space, i.e., it is intrinsically of low-dimension. The original data is assumed to be mapped from a low-dimensional space through a low-to-high-dimensional generator. In this work, we propound how to design such a low-to-high dimensional deep learning-based generator suiting for compressed sensing, while satisfying robustness to universal adversarial perturbations in the latent domain. We also justify why the noise is considered in the latent space. The work is also buttressed with theoretical analysis on the robustness of the trained generator to adversarial perturbations. Experiments on real-world datasets are provided to substantiate the efficacy of the proposed \emph{generative model adversarial training for deep compressed sensing.}