Amortized Variational Compressive Sensing
نویسندگان
چکیده
The goal of statistical compressive sensing is to efficiently acquire and reconstruct high-dimensional signals with much fewer measurements, given access to a finite set of training signals from the underlying domain being sensed. We present a novel algorithmic framework based on autoencoders that jointly learns the acquisition (a.k.a. encoding) and recovery (a.k.a. decoding) functions while implicitly modeling domain structure. Our learning objective maximizes a variational lower bound to the mutual information between the signal and the measurements. Empirically, we show 20− 46% improvement in reconstruction accuracies over competing approaches on the MNIST dataset for the same number of measurements.
منابع مشابه
Compressive Sensing for Cluster Structured Sparse Signals: Variational Bayes Approach
Compressive Sensing (CS) provides a new paradigm of sub-Nyquist sampling which can be considered as an alternative to Nyquist sampling theorem. In particular, providing that signals are with sparse representations in some known space (or domain), information can be perfectly preserved even with small amount of measurements captured by random projections. Besides sparsity prior of signals, the i...
متن کاملSemi-Amortized Variational Autoencoders
Amortized variational inference (AVI) replaces instance-specific local inference with a global inference network. While AVI has enabled efficient training of deep generative models such as variational autoencoders (VAE), recent empirical work suggests that inference networks can produce suboptimal variational parameters. We propose a hybrid approach, to use AVI to initialize the variational par...
متن کاملA Distributed Sparse Signal Reconstruction Algorithm in Wireless Sensor Network
We address the sparse signal reconstruction problem over networked sensing system. Signal acquisition is performed as in compressive sensing (CS), hence the number of measurements is reduced. Majority of existing algorithms are developed based on p minimization in the framework of distributed convex optimization and thus whose performance is sensitive to the tuning of additional parameters. In ...
متن کاملA novel compound regularization and fast algorithm for compressive sensing deconvolution
Compressive Sensing Deconvolution (CS-Deconvolution) is a new challenge problem encountered in a wide variety of image processing fields. Since CS is more efficient for sparse signals, in our scheme, the input image is firstly sparse represented by curvelet frame system; then the curvelet coefficients are encoded by a structurally random matrix based CS sampling technique. In order to improve t...
متن کاملBayesian Multi-Task Compressive Sensing with Dirichlet Process Priors
Compressive sensing (CS) is an emerging field that, under appropriate conditions, can significantly reduce the number of measurements required for a given signal. Specifically, if the m-dimensional signal u is sparse in an orthonormal basis represented by the m × m matrix Ψ, then one may infer u based on n m projection measurements. If u = Ψθ, where θ are the sparse coefficients in basis Ψ, the...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2018