arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.04158eess.IVcs.CV
收藏

基于熵注意力与感受野增强的高效单图像超分辨率

Efficient Single Image Super-Resolution with Entropy Attention and Receptive Field Augmentation

Southwest Jiaotong University(西南交通大学);Megvii Technology(旷视科技);University of Electronic Science and Technology of China(电子科技大学)

Xiaole Zhao, Linze Li, Chengxing Xie, Xiaoming Zhang, Ting Jiang, Wenjie Lin, Shuaicheng Liu, Tianrui Li

AI总结:

本文提出EARFA网络,通过熵注意力和移位大核注意力在降低计算复杂度的同时提升单图像超分辨率效率与性能。

摘要:

近年来,基于Transformer的单图像超分辨率(SISR)深度模型极大地提升了轻量级SISR任务的性能。然而,由于多头自注意力(MSA)计算复杂,它们往往承受沉重的计算负担和缓慢的推理速度,严重阻碍了其实际应用与部署。在本工作中,我们提出了一种高效的超分辨率模型,以缓解模型效率与超分辨率性能之间的两难困境,该模型被称为熵注意力与感受野增强网络(EARFA),由一个新颖的熵注意力(EA)和一个移位大核注意力(SLKA)组成。从信息论的角度来看,EA在服从高斯分布的条件下增加了中间特征的熵,为后续推理提供了更具信息量的输入。另一方面,SLKA借助通道移位扩展了超分辨率模型的感受野,同时也有利于提升层次特征的多样性。由于EA和SLKA的实现不涉及复杂计算(如大量矩阵乘法),所提方法能够在保持更好超分辨率性能的同时,实现比基于Transformer的超分辨率模型更快的非线性推理。大量实验表明,所提模型能够显著降低模型推理延迟,同时取得与其他先进模型相当的超分辨率性能。

英文摘要:

Transformer-based deep models for single image super-resolution (SISR) have greatly improved the performance of lightweight SISR tasks in recent years. However, they often suffer from heavy computational burden and slow inference due to the complex calculation of multi-head self-attention (MSA), seriously hindering their practical application and deployment. In this work, we present an efficient SR model to mitigate the dilemma between model efficiency and SR performance, which is dubbed Entropy Attention and Receptive Field Augmentation network (EARFA), and composed of a novel entropy attention (EA) and a shifting large kernel attention (SLKA). From the perspective of information theory, EA increases the entropy of intermediate features conditioned on a Gaussian distribution, providing more informative input for subsequent reasoning. On the other hand, SLKA extends the receptive field of SR models with the assistance of channel shifting, which also favors to boost the diversity of hierarchical features. Since the implementation of EA and SLKA does not involve complex computations (such as extensive matrix multiplications), the proposed method can achieve faster nonlinear inference than Transformer-based SR models while maintaining better SR performance. Extensive experiments show that the proposed model can significantly reduce the delay of model inference while achieving the SR performance comparable with other advanced models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑