Large Kernel Distillation Network for Efficient Single Image Super-Resolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xie, Chengxing, Zhang, Xiaoming, Li, Linze, Meng, Haiteng, Zhang, Tianlin, Li, Tianrui, Zhao, Xiaole
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909262348812288
author Xie, Chengxing
Zhang, Xiaoming
Li, Linze
Meng, Haiteng
Zhang, Tianlin
Li, Tianrui
Zhao, Xiaole
author_facet Xie, Chengxing
Zhang, Xiaoming
Li, Linze
Meng, Haiteng
Zhang, Tianlin
Li, Tianrui
Zhao, Xiaole
contents Efficient and lightweight single-image super-resolution (SISR) has achieved remarkable performance in recent years. One effective approach is the use of large kernel designs, which have been shown to improve the performance of SISR models while reducing their computational requirements. However, current state-of-the-art (SOTA) models still face problems such as high computational costs. To address these issues, we propose the Large Kernel Distillation Network (LKDN) in this paper. Our approach simplifies the model structure and introduces more efficient attention modules to reduce computational costs while also improving performance. Specifically, we employ the reparameterization technique to enhance model performance without adding extra cost. We also introduce a new optimizer from other tasks to SISR, which improves training speed and performance. Our experimental results demonstrate that LKDN outperforms existing lightweight SR methods and achieves SOTA performance.
format Preprint
id arxiv_https___arxiv_org_abs_2407_14340
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Large Kernel Distillation Network for Efficient Single Image Super-Resolution
Xie, Chengxing
Zhang, Xiaoming
Li, Linze
Meng, Haiteng
Zhang, Tianlin
Li, Tianrui
Zhao, Xiaole
Image and Video Processing
Computer Vision and Pattern Recognition
Efficient and lightweight single-image super-resolution (SISR) has achieved remarkable performance in recent years. One effective approach is the use of large kernel designs, which have been shown to improve the performance of SISR models while reducing their computational requirements. However, current state-of-the-art (SOTA) models still face problems such as high computational costs. To address these issues, we propose the Large Kernel Distillation Network (LKDN) in this paper. Our approach simplifies the model structure and introduces more efficient attention modules to reduce computational costs while also improving performance. Specifically, we employ the reparameterization technique to enhance model performance without adding extra cost. We also introduce a new optimizer from other tasks to SISR, which improves training speed and performance. Our experimental results demonstrate that LKDN outperforms existing lightweight SR methods and achieves SOTA performance.
title Large Kernel Distillation Network for Efficient Single Image Super-Resolution
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.14340