Abstract
This paper studies interpretability of convolutional networks by means of saliency maps. Most approaches based on Class Activation Maps (CAM) combine information from fully connected layers and gradient through variants of backpropagation. However, it is well understood that gradients are noisy and alternatives like guided backpropagation have been proposed to obtain better visualization at inference. In this work, we present a novel training approach to improve the quality of gradients for interpretability. In particular, we introduce a regularization loss such that the gradient with respect to the input image obtained by standard backpropagation is similar to the gradient obtained by guided backpropagation. We find that the resulting gradient is qualitatively less noisy and improves quantitatively the interpretability properties of different networks, using several interpretability methods.
Abstract (translated)
本文通过关注卷积神经网络的清晰度图来研究可解释性。大多数基于类激活图（CAM）的方法结合了全连接层的信息和反向传播中的梯度。然而，人们普遍认为梯度是噪声，因此出现了类似于指导反向传播（GSP）的方法来获得更好的推理可视化。在这项工作中，我们提出了一个新颖的训练方法来提高梯度的质量。特别地，我们引入了一个正则化损失，使得通过标准反向传播获得的输入图像的梯度与通过指导反向传播获得的梯度相似。我们发现，通过这种方法得到的梯度在质上是更少的噪声，并且通过使用几种可解释性方法，提高了不同网络的定量可解释性特性。
URL
https://arxiv.org/abs/2404.15024
