Optimized highway deep learning network for fast single image super-resolution reconstruction

Viet Khanh Ha, Jinchang Ren, Xinying Xu, Wenzhi Liao, Sophia Zhao, Jie Ren, Gaowei Yan

Research output: Contribution to journalArticlepeer-review

Abstract

With the success of the deep residual network for image recognition tasks, the residual connection or skip connection has been widely used in deep learning models for various vision tasks, including single image super-resolution (SISR). Most existing SISR approaches pay particular attention to residual learning, while few studies investigate highway connection for SISR. Although skip connection can help to alleviate the vanishing gradient problem and enable fast training of the deep network, it still provides the coarse level of approximation in both forward and backward propagation paths and thus challenging to recover high-frequency details. To address this issue, we propose a novel model for SISR by using highway connection (HNSR), which composes of a nonlinear gating mechanism to further regulate the information. By using the global residual learning and replacing all local residual learning with designed gate unit in highway connection, HNSR has the capability of efficiently learning different hierarchical features and recovering much more details in image reconstruction. The experimental results have validated that HNSR can provide not only improved quality but also less prone to a few common problems during training. Besides, the more robust and efficient model is suitable for implementation in real-time and mobile systems.

Original languageEnglish
Pages (from-to)1961-1970
Number of pages10
JournalJournal of Real-Time Image Processing
Volume17
Issue number6
Early online date27 Apr 2020
DOIs
Publication statusPublished - 31 Dec 2020

Keywords

  • image processing
  • single image super resolution
  • highway connection
  • residual learning
  • gating mechanism

Fingerprint Dive into the research topics of 'Optimized highway deep learning network for fast single image super-resolution reconstruction'. Together they form a unique fingerprint.

Cite this