Deep Blind Compressed Sensing
This addresses a bottleneck in compressive sensing for researchers and practitioners by enabling direct deep learning on compressed data, though it appears incremental as it builds on existing deep matrix factorization and blind compressed sensing frameworks.
The paper tackles the problem of extracting learned features directly from compressive measurements, bypassing the need for signal reconstruction, and shows that this approach yields considerably better results across imaging and biomedical signal applications.
This work addresses the problem of extracting deeply learned features directly from compressive measurements. There has been no work in this area. Existing deep learning tools only give good results when applied on the full signal, that too usually after preprocessing. These techniques require the signal to be reconstructed first. In this work we show that by learning directly from the compressed domain, considerably better results can be obtained. This work extends the recently proposed framework of deep matrix factorization in combination with blind compressed sensing; hence the term deep blind compressed sensing. Simulation experiments have been carried out on imaging via single pixel camera, under-sampled biomedical signals, arising in wireless body area network and compressive hyperspectral imaging. In all cases, the superiority of our proposed deep blind compressed sensing can be envisaged.