Two Strategies Toward Lightweight Image Super-Resolution

Zongcai Du; Jie Liu; Jie Tang; Gangshan Wu

ICASSP 2022accepted0 citations

Two Strategies Toward Lightweight Image Super-Resolution

Zongcai Du, Jie Liu, Jie Tang, Gangshan Wu

Abstract

Recent convolution neural networks (CNNs) have achieved remarkable success in lightweight image super-resolution (LISR). The goal of LISR is to restore more accurate details with less model capacity. However, we observe two phenomena in current micro-architectures, one is the lack of consistent learning ability of high-frequency components, the other is large residual problem which does harm to the stability of residual learning. To tackle the two issues, we propose two strategies, namely global-guided attention strategy (GGAS) and channel-wise scaling strategy (CWSS), which can significantly improve the performance of the state-of-the-arts with negligible overheads.

BibTeX

@inproceedings{icassp2022_twostrategiestow,
  title = {Two Strategies Toward Lightweight Image Super-Resolution},
  author = {Zongcai Du and Jie Liu and Jie Tang and Gangshan Wu},
  booktitle = {ICASSP 2022},
  year = {2022}
}