Improved differentiable neural architecture search for single image super-resolution

• Published in: Peer-to-peer networking and applications Vol. 14; no. 3; pp. 1806 - 1815
• Main Authors: Weng, Yu, Chen, Zehua, Zhou, Tianbao
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.05.2021; Springer Nature B.V
• Subjects: Algorithms; Communications Engineering; Computer Communication Networks; Convolution; Datasets; Engineering; Image resolution; Information Systems and Communication Service; Machine learning; Networks; Redesign; Searching; Signal,Image and Speech Processing; Special Issue on P2P Computing for Deep Learning; DARTS; SISR; Convolution cell; Nonlinear mapping part
• ISSN: 1936-6442; 1936-6450
• DOI: 10.1007/s12083-020-01048-4

Deep learning has shown prominent superiority over other machine learning algorithms in Single Image Super-Resolution (SISR). In order to reduce the efforts and resources cost on manually designing deep architecture, we use differentiable neural architecture search (DARTS) on SISR. Since neural architecture search was originally used for classification tasks, our experiments show that direct usage of DARTS on super-resolutions tasks will give rise to many skip connections in the search architecture, which results in the poor performance of final architecture. Thus, it is necessary for DARTS to have made some improvements for the application in the field of SISR. According to characteristics of SISR, we remove redundant operations and redesign some operations in the cell to achieve an improved DARTS. Then we use the improved DARTS to search convolution cells as a nonlinear mapping part of super-resolution network. The new super-resolution architecture shows its effectiveness on benchmark datasets and DIV2K dataset.