论文标题
伴随示意图：使用伴随操作员从CNN层重建有效的决策高度曲面
AdjointBackMap: Reconstructing Effective Decision Hypersurfaces from CNN Layers Using Adjoint Operators
论文作者
论文摘要
有几种有效的方法来解释卷积神经网络（CNN）的内部工作。但是，通常，发现CNN整体执行的函数的倒数是一个不适的问题。在本文中，我们提出了一种基于伴随运算符的方法以重建，鉴于CNN中的任意单元（第一个卷积层除外），在输入空间中，其有效的超出表面可以复制该单元的决策表面在特定的输入图像上。我们的结果表明，当以这种方式重建Hypersurface时，当乘以原始输入图像时，几乎可以给出该单元的确切输出值。我们发现，CNN单元的决策表面在很大程度上是在输入上的，这可以解释为什么对抗性输入可以有效地欺骗CNN。
There are several effective methods in explaining the inner workings of convolutional neural networks (CNNs). However, in general, finding the inverse of the function performed by CNNs as a whole is an ill-posed problem. In this paper, we propose a method based on adjoint operators to reconstruct, given an arbitrary unit in the CNN (except for the first convolutional layer), its effective hypersurface in the input space that replicates that unit's decision surface conditioned on a particular input image. Our results show that the hypersurface reconstructed this way, when multiplied by the original input image, would give nearly the exact output value of that unit. We find that the CNN unit's decision surface is largely conditioned on the input, and this may explain why adversarial inputs can effectively deceive CNNs.
