Lightweight Image Super-Resolution via Weighted Multi-Scale Residual Network

The tradeoff between efficiency and model size of the convolutional neural network (CNN) is an essential issue for applications of CNN-based algorithms to diverse real-world tasks. Although deep learning-based methods have achieved significant improvements in image super-resolution (SR), current CNN...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE/CAA journal of automatica sinica 2021-07, Vol.8 (7), p.1271-1280
Hauptverfasser: Sun, Long, Liu, Zhenbing, Sun, Xiyan, Liu, Licheng, Lan, Rushi, Luo, Xiaonan
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The tradeoff between efficiency and model size of the convolutional neural network (CNN) is an essential issue for applications of CNN-based algorithms to diverse real-world tasks. Although deep learning-based methods have achieved significant improvements in image super-resolution (SR), current CNN-based techniques mainly contain massive parameters and a high computational complexity, limiting their practical applications. In this paper, we present a fast and lightweight framework, named weighted multi-scale residual network (WMRN), for a better tradeoff between SR performance and computational efficiency. With the modified residual structure, depthwise separable convolutions (DS Convs) are employed to improve convolutional operations' efficiency. Furthermore, several weighted multi-scale residual blocks (WMRBs) are stacked to enhance the multi-scale representation capability. In the reconstruction subnetwork, a group of Conv layers are introduced to filter feature maps to reconstruct the final high-quality image. Extensive experiments were conducted to evaluate the proposed model, and the comparative results with several state-of-the-art algorithms demonstrate the effectiveness of WMRN.
ISSN:2329-9266
2329-9274
DOI:10.1109/JAS.2021.1004009