Deep convolutional neural networks are a powerful model class for a range of computer vision problems, but it is difficult to interpret the image filtering process they implement, given their sheer size. In this work, we introduce a method for extracting 'feature-preserving circuits' from deep CNNs, leveraging methods from saliency-based neural network pruning. These circuits are modular sub-functions, embedded within the network, containing only a subset of convolutional kernels relevant to a target feature. We compare the efficacy of 3 saliency-criteria for extracting these sparse circuits. Further, we show how 'sub-feature' circuits can be extracted, that preserve a feature's responses to particular images, dividing the feature into even sparser filtering processes. We also develop a tool for visualizing 'circuit diagrams', which render the entire image filtering process implemented by circuits in a parsable format.
翻译:----
深度卷积神经网络是一种强大的模型类,用于解决各种计算机视觉问题,但由于其规模巨大,很难解释它们实现的图像过滤过程。在这项工作中,我们介绍了一种从深度卷积神经网络中提取'特征保留电路'的方法,利用基于显著性的神经网络剪枝方法。这些电路是嵌入在网络中的模块化子函数,仅包含与目标特征相关的卷积核的子集。我们比较了提取这些稀疏电路的3个显著性标准的功效。此外,我们展示了如何提取'子特征'电路,保留特征对特定图像的响应,将特征分成更稀疏的过滤过程。我们还开发了一种可视化'电路图'的工具,将电路实现的整个图像过滤过程呈现为可分析格式。