Learning to optimize (L2O) is an emerging approach that leverages machine learning to
develop optimization methods, aiming at reducing the laborious iterations of hand …

In recent years, unfolding iterative algorithms as neural networks has become an empirical
success in solving sparse recovery problems. However, its theoretical understanding is still …

Deep neural networks based on unfolding an iterative algorithm, for example, LISTA
(learned iterative shrinkage thresholding algorithm), have been an empirical success for …

Single image dehazing has been a classic topic in computer vision for years. Motivated by
the atmospheric scattering model, the key to satisfactory single image dehazing relies on an …

One major assumption used in most existing hashing approaches is that the domain of
interest (ie, the target domain) could provide sufficient training data, either labeled or …

Purpose Dual‐energy CT (DECT) has been increasingly used in imaging applications
because of its capability for material differentiation. However, material decomposition suffers …

Natural language understanding and dialogue policy learning are both essential in
conversational systems that predict the next system actions in response to a current user …

Single image rain-streak removal is an extremely challenging problem due to the presence
of non-uniform rain densities in images. Previous works solve this problem using various …

Tensor factorization is a useful technique for capturing the high-order interactions in data
analysis. One assumption of tensor decompositions is that a predefined rank should be …

Diffusion magnetic resonance imaging (dMRI) offers a unique tool for noninvasively
assessing tissue microstructure. However, accurate estimation of tissue microstructure …