论文标题
用本地归因地图解释超分辨率网络
Interpreting Super-Resolution Networks with Local Attribution Maps
论文作者
论文摘要
图像超分辨率（SR）技术一直在迅速发展，从深网的发明及其连续的突破中受益。但是，公认的是，深度学习和深度神经网络很难解释。 SR网络继承了这种神秘的性质，很少的作品试图理解它们。在本文中，我们对SR网络进行归因分析，该分析旨在寻找强烈影响SR结果的输入像素。我们提出了一种称为本地归因图（LAM）的新型归因方法，该方法继承了积分梯度方法，但具有两个独特的特征。一种是将模糊图像用作基线输入，另一个是采用渐进模糊函数作为路径函数。基于LAM，我们表明：（1）具有更大涉及的输入像素的SR网络可以实现更好的性能。 （2）注意网络和非本地网络从更广泛的输入像素范围提取特征。 （3）与实际贡献的范围进行比较，对于大多数深层网络而言，接收场足够大。 （4）对于SR网络，更可能注意到具有常规条纹或网格的纹理，而复杂的语义很难使用。我们的工作打开了新的方向，用于设计SR网络和解释低级视觉深度模型。
Image super-resolution (SR) techniques have been developing rapidly, benefiting from the invention of deep networks and its successive breakthroughs. However, it is acknowledged that deep learning and deep neural networks are difficult to interpret. SR networks inherit this mysterious nature and little works make attempt to understand them. In this paper, we perform attribution analysis of SR networks, which aims at finding the input pixels that strongly influence the SR results. We propose a novel attribution approach called local attribution map (LAM), which inherits the integral gradient method yet with two unique features. One is to use the blurred image as the baseline input, and the other is to adopt the progressive blurring function as the path function. Based on LAM, we show that: (1) SR networks with a wider range of involved input pixels could achieve better performance. (2) Attention networks and non-local networks extract features from a wider range of input pixels. (3) Comparing with the range that actually contributes, the receptive field is large enough for most deep networks. (4) For SR networks, textures with regular stripes or grids are more likely to be noticed, while complex semantics are difficult to utilize. Our work opens new directions for designing SR networks and interpreting low-level vision deep models.
