Deep Learning Sparse Ternary Projections for Compressed Sensing of Images
This work addresses the need for efficient hardware implementations of compressed sensing in image processing, though it is incremental as it builds on existing deep learning and ternary projection methods.
The paper tackled the problem of designing sparse ternary projection matrices for compressed sensing of images, which are more hardware-friendly than traditional random Gaussian matrices, and achieved state-of-the-art results with significant complexity advantages.
Compressed sensing (CS) is a sampling theory that allows reconstruction of sparse (or compressible) signals from an incomplete number of measurements, using of a sensing mechanism implemented by an appropriate projection matrix. The CS theory is based on random Gaussian projection matrices, which satisfy recovery guarantees with high probability; however, sparse ternary {0, -1, +1} projections are more suitable for hardware implementation. In this paper, we present a deep learning approach to obtain very sparse ternary projections for compressed sensing. Our deep learning architecture jointly learns a pair of a projection matrix and a reconstruction operator in an end-to-end fashion. The experimental results on real images demonstrate the effectiveness of the proposed approach compared to state-of-the-art methods, with significant advantage in terms of complexity.