面向图像超分辨率的带分布变换的序列分层学习
Sequential Hierarchical Learning with Distribution Transformation for Image Super-Resolution
AI总结：
针对图像超分辨率任务，提出结合序列多尺度模块与分布变换模块的SHSR网络，高效挖掘分层特征，在×4倍率下以更少参数和运算量取得优于现有方法的性能，自集成扩展版SHSR⁺效果更具竞争力。
摘要：
近年来的图像超分辨率（SR）研究采用多尺度设计来挖掘分层特征信息。现有多尺度网络旨在构建精细的模块或渐进式架构以实现重建。通常而言，更大尺度的特征更关注结构与高层信息，而更小尺度的特征包含丰富的细节与纹理信息。从这一角度来看，大尺度特征的信息可由小尺度特征推导得到。基于该观察，本文构建了序列分层学习超分辨率网络（SHSR）以实现高效的图像超分辨率。具体而言，我们考虑特征的尺度间相关性，设计了序列多尺度模块（SMB）以渐进式挖掘分层信息。SMB基于卷积的线性特性以递归方式设计，参数规模受限。除了序列分层学习，我们还探究了特征图之间的相关性，设计了分布变换模块（DTB）。与基于注意力的方法不同，DTB以归一化的方式处理变换，结合缩放与偏置因子共同考量空间与通道维度的相关性。实验结果表明，在放大倍数为×4时，SHSR相比当前最优方法取得了更优的量化性能与视觉质量，同时参数减少近34%，乘加运算量（MACs）减少近50%。为在不额外训练的情况下提升性能，带自集成的扩展模型SHSR⁺在×4放大倍数下，相比更大规模的网络取得了具有竞争力的性能，同时参数减少近92%，MACs减少近42%。
英文摘要：
Multi-scale design has been considered in recent image super-resolution (SR) works to explore the hierarchical feature information. Existing multi-scale networks aim to build elaborate blocks or progressive architecture for restoration. In general, larger scale features concentrate more on structural and high-level information, while smaller scale features contain plentiful details and textured information. In this point of view, information from larger scale features can be derived from smaller ones. Based on the observation, in this paper, we build a sequential hierarchical learning super-resolution network (SHSR) for effective image SR. Specially, we consider the inter-scale correlations of features, and devise a sequential multi-scale block (SMB) to progressively explore the hierarchical information. SMB is designed in a recursive way based on the linearity of convolution with restricted parameters. Besides the sequential hierarchical learning, we also investigate the correlations among the feature maps and devise a distribution transformation block (DTB). Different from attention-based methods, DTB regards the transformation in a normalization manner, and jointly considers the spatial and channel-wise correlations with scaling and bias factors. Experiment results show SHSR achieves superior quantitative performance and visual quality to state-of-the-art methods with near 34\% parameters and 50\% MACs off when scaling factor is $\times4$. To boost the performance without further training, the extension model SHSR$^+$ with self-ensemble achieves competitive performance than larger networks with near 92\% parameters and 42\% MACs off with scaling factor $\times4$.
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。
