EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

High-frequency channel attention and contrastive learning for image super-resolution

Tianyu Yan, Hujun Yin

The Visual Computer · 2024-12 · 40 (12) · 8839-8851

DOI: 10.1007/s00371-024-03276-8 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Visual Computer, online erschienen am 29.02.2024. Verfasst von Tianyu Yan und 1 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Over the last decade, convolutional neural networks (CNNs) have allowed remarkable advances in single image super-resolution (SISR). In general, recovering high-frequency features is crucial for high-performance models. High-frequency features suffer more serious damages than low-frequency features during downscaling, making it hard to recover edges and textures. In this paper, we attempt to guide the network to focus more on high-frequency features in restoration from both channel and spatial perspectives. Specifically, we propose a high-frequency channel attention (HFCA) module and a frequency contrastive learning (FCL) loss to aid the process. For the channel-wise perspective, the HFCA module rescales channels by predicting statistical similarity metrics of the feature maps and their high-frequency components. For the spatial perspective, the FCL loss introduces contrastive learning to train a spatial mask that adaptively assigns high-frequency areas with large scaling factors. We incorporate the proposed HFCA module and FCL loss into an EDSR baseline model to construct the proposed lightweight high-frequency channel contrastive network (HFCCN). Extensive experimental results show that it can yield markedly improved or competitive performances compared to the state-of-the-art networks of similar model parameters.

Zitieren

APA

Yan, T., & Yin, H. (2024). High-frequency channel attention and contrastive learning for image super-resolution. The Visual Computer, 40(12), 8839-8851. https://doi.org/10.1007/s00371-024-03276-8

Vancouver

Yan T, Yin H. High-frequency channel attention and contrastive learning for image super-resolution. The Visual Computer. 2024;40(12):8839-8851. doi:10.1007/s00371-024-03276-8

BibTeX
@article{Yan2024,
  author = {Yan, Tianyu and Yin, Hujun},
  title = {High-frequency channel attention and contrastive learning for image super-resolution},
  journal = {The Visual Computer},
  year = {2024},
  volume = {40},
  number = {12},
  pages = {8839--8851},
  doi = {10.1007/s00371-024-03276-8}
}
Kostenlos starten →