Non-Local Attention (NLA) brings significant improvement for Single Image Super-Resolution (SISR) by leveraging intrinsic feature correlation in natural images. However, NLA gives noisy information large weights and consumes quadratic computation resources with respect to the input size, limiting its performance and application. In this paper, we propose a novel Efficient Non-Local Contrastive Attention (ENLCA) to perform long-range visual modeling and leverage more relevant non-local features. Specifically, ENLCA consists of two parts, Efficient Non-Local Attention (ENLA) and Sparse Aggregation. ENLA adopts the kernel method to approximate exponential function and obtains linear computation complexity. For Sparse Aggregation, we multiply inputs by an amplification factor to focus on informative features, yet the variance of approximation increases exponentially. Therefore, contrastive learning is applied to further separate relevant and irrelevant features. To demonstrate the effectiveness of ENLCA, we build an architecture called Efficient Non-Local Contrastive Network (ENLCN) by adding a few of our modules in a simple backbone. Extensive experimental results show that ENLCN reaches superior performance over state-of-the-art approaches on both quantitative and qualitative evaluations.
翻译:非本地注意(NLA)通过利用自然图像的内在特征相关性,大大改进了单一图像超分辨率(SISR),使自然图像的内在特征相关性;然而,NLA在输入大小方面提供了大量信息,并消耗了量度计算资源,限制了其性能和应用;在本文中,我们建议采用新的高效非本地差异关注(ENLA),以进行远程视觉模型建模,并利用更相关的非本地特征;具体地说,ENLACA由两个部分组成,即高效非本地注意(ENLA)和散射聚合。ENLA采用内核法以近似指数函数,并获得线性计算复杂性。在粗略的聚合方面,我们将投入增加一个放大系数,以侧重于信息性特征,但近似性增长成指数。因此,对比性学习应用于进一步的分别相关和不相干的特点。为了证明ENLACA的有效性,我们建立了一个称为高效非本地兼容网络(ENLCN)的结构,在简单的主干线中增加了几个模块。广泛的实验结果显示,ENLCN在定量和定性方法上都达到了优异性。