计算机科学
二次增长
变压器
图像分辨率
杠杆(统计)
计算复杂性理论
推论
计算机工程
算法
人工智能
模式识别(心理学)
电压
工程类
电气工程
作者
Kun Zeng,Hanjiang Lin,Zhiqiang Yan,Jinsheng Fang
标识
DOI:10.1109/tim.2023.3304672
摘要
Image super-resolution (SR) is the process of restoring high-resolution (HR) images from low-resolution (LR) ones. Recent Transformer-based SR methods have achieved impressive results by utilizing the self-attention (SA) mechanism, which allows modeling long-range dependencies among input features in spatial dimensions. However, the computational complexity of SA increases quadratically with respect to the feature size, which makes Transformer-based methods inefficient. Additionally, despite the success of dense connections in CNN-based methods, they have not been fully explored in Transformer-based methods. In this paper, we propose a novel approach for lightweight SR, called Densely Connected Transformer with Linear Self-Attention (DCTLSA) network. Our method addresses the efficiency issue of SA by designing a new linear SA, which calculates the similarities in spatial dimension with linear complexity. Moreover, we leverage dense connections to integrate multiple levels of features and provide rich information for SR. Our experimental results demonstrate that DCTLSA outperforms state-of-the-art lightweight SR methods in terms of SR performance, model complexity, and inference speed. The code of the proposed method is available at https://github.com/zengkun301/DCTLSA.
科研通智能强力驱动
Strongly Powered by AbleSci AI