Feature Distillation Interaction Weighting Network for Lightweight Image Super-resolution

Authors

  • Guangwei Gao Nanjing University of Posts and Telecommunications
  • Wenjie Li Nanjing University of Posts and Telecommunications
  • Juncheng Li The Chinese University of Hong Kong
  • Fei Wu Nanjing University of Posts and Telecommunications
  • Huimin Lu Kyushu Institute of Technology
  • Yi Yu National Institute of Informatics

DOI:

https://doi.org/10.1609/aaai.v36i1.19946

Keywords:

Computer Vision (CV)

Abstract

Convolutional neural networks based single-image superresolution (SISR) has made great progress in recent years. However, it is difficult to apply these methods to real-world scenarios due to the computational and memory cost. Meanwhile, how to take full advantage of the intermediate features under the constraints of limited parameters and calculations is also a huge challenge. To alleviate these issues, we propose a lightweight yet efficient Feature Distillation Interaction Weighted Network (FDIWN). Specifically, FDIWN utilizes a series of specially designed Feature Shuffle Weighted Groups (FSWG) as the backbone, and several novel mutual Wide-residual Distillation Interaction Blocks (WDIB) form an FSWG. In addition, Wide Identical Residual Weighting (WIRW) units and Wide Convolutional Residual Weighting (WCRW) units are introduced into WDIB for better feature distillation. Moreover, a Wide-Residual Distillation Connection (WRDC) framework and a Self-Calibration Fusion (SCF) unit are proposed to interact features with different scales more flexibly and efficiently. Extensive experiments show that our FDIWN is superior to other models to strike a good balance between model performance and efficiency. The code is available at https://github.com/IVIPLab/FDIWN.

Downloads

Published

2022-06-28

How to Cite

Gao, G., Li, W., Li, J., Wu, F., Lu, H., & Yu, Y. (2022). Feature Distillation Interaction Weighting Network for Lightweight Image Super-resolution. Proceedings of the AAAI Conference on Artificial Intelligence, 36(1), 661-669. https://doi.org/10.1609/aaai.v36i1.19946

Issue

Section

AAAI Technical Track on Computer Vision I