论文标题
在CNN中修剪保留功能的电路
Pruning for Feature-Preserving Circuits in CNNs
论文作者
论文摘要
深度卷积神经网络是针对一系列计算机视觉问题的强大模型类，但是考虑到它们的大小，很难解释其实现的图像过滤过程。在这项工作中，我们介绍了一种从Deep CNN中提取“功能保护电路”的方法，从而利用了基于显着性的神经网络修剪的方法。这些电路是模块化的子功能，嵌入了网络中，仅包含与目标特征相关的卷积内核的子集。我们比较了3个显着性标准在提取这些稀疏电路的功效。此外，我们展示了如何提取“子功能”电路，从而保留功能对特定图像的响应，从而将功能划分为甚至更稀疏的过滤过程。我们还开发了一种可视化“电路图”的工具，该工具渲染了由电路以可播放格式实现的整个图像过滤过程。
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.
