arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.11937eess.IVcs.CV
收藏

基于多粒度注意力网络的单幅图像超分辨率处理

Multi-grained Attention Networks for Single Image Super-Resolution

Nanjing University of Science and Technology(南京理工大学);University of Michigan(密歇根大学);DiDi AI Labs, DiDi Chuxing(滴滴出行人工智能实验室)

Huapeng Wu, Zhengxia Zou, Jie Gui, Wen-Jun Zeng, Jieping Ye, Jun Zhang, Hongyi Liu, Zhihui Wei

摘要:

深度卷积神经网络(CNN)在图像超分辨率(SR)方面引起了广泛的关注。最近,视觉注意机制,利用特征重要性和上下文线索,已被引入到图像SR,并证明是有效的,以提高基于CNN的SR性能。在本文中,我们对SR模型中的注意机制进行了深入的研究,并阐明了这些想法的简单而有效的改进如何提高最先进的水平。我们进一步提出了一个统一的方法,称为“多粒度的注意力网络(MGAN)”,充分利用SR任务的多尺度和注意力机制的优势。在我们的方法中,每个神经元的重要性是根据其周围的区域在多粒度的方式计算,然后被用来自适应地重新缩放的特征响应。更重要的是,以往方法中的“通道注意”和“空间注意”策略本质上可以看作是我们方法的两个特例。我们还引入了多尺度稠密连接来提取多尺度下的图像特征,并通过稠密跳跃连接来捕获不同层的特征。基准数据集上的消融研究证明了我们的方法的有效性。在与其他国家的最先进的SR方法相比,我们的方法显示的优越性,在精度和模型大小。

英文摘要:

Deep Convolutional Neural Networks (CNN) have drawn great attention in image super-resolution (SR). Recently, visual attention mechanism, which exploits both of the feature importance and contextual cues, has been introduced to image SR and proves to be effective to improve CNN-based SR performance. In this paper, we make a thorough investigation on the attention mechanisms in a SR model and shed light on how simple and effective improvements on these ideas improve the state-of-the-arts. We further propose a unified approach called "multi-grained attention networks (MGAN)" which fully exploits the advantages of multi-scale and attention mechanisms in SR tasks. In our method, the importance of each neuron is computed according to its surrounding regions in a multi-grained fashion and then is used to adaptively re-scale the feature responses. More importantly, the "channel attention" and "spatial attention" strategies in previous methods can be essentially considered as two special cases of our method. We also introduce multi-scale dense connections to extract the image features at multiple scales and capture the features of different layers through dense skip connections. Ablation studies on benchmark datasets demonstrate the effectiveness of our method. In comparison with other state-of-the-art SR methods, our method shows the superiority in terms of both accuracy and model size.

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。

↑