Efficient Non-local Contrastive Attention for Image Super-resolution

Authors

  • Bin Xia Shenzhen International Graduate School / Department of Electronic Engineering, Tsinghua University
  • Yucheng Hang Shenzhen International Graduate School / Department of Electronic Engineering, Tsinghua University
  • Yapeng Tian University of Rochester
  • Wenming Yang Shenzhen International Graduate School / Department of Electronic Engineering, Tsinghua University
  • Qingmin Liao Shenzhen International Graduate School / Department of Electronic Engineering, Tsinghua University
  • Jie Zhou Department of Automation, Tsinghua University

DOI:

https://doi.org/10.1609/aaai.v36i3.20179

Keywords:

Computer Vision (CV)

Abstract

Non-Local Attention (NLA) brings significant improvement for Single Image Super-Resolution (SISR) by leveraging intrinsic feature correlation in natural images. However, NLA gives noisy information large weights and consumes quadratic computation resources with respect to the input size, limiting its performance and application. In this paper, we propose a novel Efficient Non-Local Contrastive Attention (ENLCA) to perform long-range visual modeling and leverage more relevant non-local features. Specifically, ENLCA consists of two parts, Efficient Non-Local Attention (ENLA) and Sparse Aggregation. ENLA adopts the kernel method to approximate exponential function and obtains linear computation complexity. For Sparse Aggregation, we multiply inputs by an amplification factor to focus on informative features, yet the variance of approximation increases exponentially. Therefore, contrastive learning is applied to further separate relevant and irrelevant features. To demonstrate the effectiveness of ENLCA, we build an architecture called Efficient Non-Local Contrastive Network (ENLCN) by adding a few of our modules in a simple backbone. Extensive experimental results show that ENLCN reaches superior performance over state-of-the-art approaches on both quantitative and qualitative evaluations.

Downloads

Published

2022-06-28

How to Cite

Xia, B., Hang, Y., Tian, Y., Yang, W., Liao, Q., & Zhou, J. (2022). Efficient Non-local Contrastive Attention for Image Super-resolution. Proceedings of the AAAI Conference on Artificial Intelligence, 36(3), 2759-2767. https://doi.org/10.1609/aaai.v36i3.20179

Issue

Section

AAAI Technical Track on Computer Vision III