We study the attribution problem [28] for deep networks applied to perception tasks. For vision tasks, attribution techniques attribute the prediction of a network to the pixels of the input image. We propose a new technique called \emph{Blur Integrated Gradients}. This technique has several advantages over other methods. First, it can tell at what scale a network recognizes an object. It produces scores in the scale/frequency dimension, that we find captures interesting phenomena. Second, it satisfies the scale-space axioms [14], which imply that it employs perturbations that are free of artifact. We therefore produce explanations that are cleaner and consistent with the operation of deep networks. Third, it eliminates the need for a 'baseline' parameter for Integrated Gradients [31] for perception tasks. This is desirable because the choice of baseline has a significant effect on the explanations. We compare the proposed technique against previous techniques and demonstrate application on three tasks: ImageNet object recognition, Diabetic Retinopathy prediction, and AudioSet audio event identification.

中文翻译：

---

规模和空间归因

我们研究了应用于感知任务的深层网络的归因问题 [28]。对于视觉任务，归因技术将网络的预测归因于输入图像的像素。我们提出了一种称为 \emph{Blur Integrated Gradients} 的新技术。与其他方法相比，该技术有几个优点。首先，它可以判断网络识别对象的规模。它在尺度/频率维度上产生分数，我们发现它捕获了有趣的现象。其次，它满足尺度空间公理 [14]，这意味着它采用了无伪影的扰动。因此，我们产生了更清晰且与深度网络的操作一致的解释。第三，它消除了感知任务对集成梯度 [31] 的“基线”参数的需要。这是可取的，因为基线的选择对解释有显着影响。我们将所提出的技术与以前的技术进行比较，并演示在三个任务上的应用：ImageNet 对象识别、糖尿病视网膜病变预测和 AudioSet 音频事件识别。