Linguistics

Philosophy

Statistics

Microeconomics

Operating system

Economics

Set (abstract data type)

Data mining

Computer science

Code (set theory)

Image resolution

Source code

Pattern recognition (psychology)

Mathematics

Image (mathematics)

Feature (linguistics)

Expectation–maximization algorithm

Block (permutation group theory)

Artificial intelligence

Geometry

Programming language

Deep learning

Maximum likelihood

Feature extraction

Maximization

Convolutional neural network

IEEE Transactions on Circuits and Systems for Video Technology

In recent years, with the rapid development of deep learning, super-resolution methods based on convolutional neural networks (CNNs) have made great progress. However, the parameters and the required consumption of computing resources of these methods are also increasing to the point that such methods are difficult to implement on devices with low computing power. To address this issue, we propose a lightweight single image super-resolution network with an expectation-maximization attention mechanism (EMASRN) for better balancing performance and applicability. Specifically, a progressive multi-scale feature extraction block (PMSFE) is proposed to extract feature maps of different sizes. Furthermore, we propose an HR-size expectation-maximization attention block (HREMAB) that directly captures the long-range dependencies of HR-size feature maps. We also utilize a feedback network to feed the high-level features of each generation into the next generation&#x2019;s shallow network. Compared with the existing lightweight single image super-resolution (SISR) methods, our EMASRN reduces the number of parameters by almost one-third. The experimental results demonstrate the superiority of our EMASRN over state-of-the-art lightweight SISR methods in terms of both quantitative metrics and visual quality. The source code can be downloaded at <uri>https://github.com/xyzhu1/EMASRN</uri>.

Lightweight Image Super-Resolution With Expectation-Maximization Attention Mechanism