赋予基于CAM的方法生成细粒度高忠实度解释的能力
Empowering CAM-Based Methods with Capability to Generate Fine-Grained and High-Faithfulness Explanations
AI总结：
针对现有CAM类方法只能生成粗粒度解释、LRP类方法解释忠实度低的问题，提出FG-CAM利用相邻层特征图关系生成细粒度高忠实度解释，在多层级表现优于现有方法，还推出去噪变体。
摘要：
近年来，神经网络模型的可解释性受到了广泛的研究关注。在计算机视觉领域，基于CAM（类激活映射）的方法和LRP（逐层相关性传播）方法是两种常见的解释方法。然而，由于大多数基于CAM的方法只能生成全局权重，它们只能在深层生成粗粒度的解释。另一方面，LRP及其变体可以生成细粒度的解释，但解释的忠实度过低。为了解决这些挑战，本文提出了FG-CAM（细粒度CAM），该方法扩展了基于CAM的方法，使其能够生成细粒度且高忠实度的解释。FG-CAM利用具有分辨率差异的相邻两层特征图之间的关系，逐步提高解释分辨率，同时找出有贡献的像素并过滤掉无贡献的像素。我们的方法不仅在不改变基于CAM的方法特性的前提下解决了它们的缺点，而且生成的细粒度解释比LRP及其变体具有更高的忠实度。我们还提出了带去噪的FG-CAM，它是FG-CAM的一个变体，能够在解释忠实度几乎不变的情况下生成噪声更少的解释。实验结果表明，FG-CAM的性能几乎不受解释分辨率的影响。FG-CAM在浅层和中间层的表现均显著优于现有基于CAM的方法，在输入层的表现显著优于LRP及其变体。我们的代码可在https://github.com/dongmo-qcq/FG-CAM获取。
英文摘要：
Recently, the explanation of neural network models has garnered considerable research attention. In computer vision, CAM (Class Activation Map)-based methods and LRP (Layer-wise Relevance Propagation) method are two common explanation methods. However, since most CAM-based methods can only generate global weights, they can only generate coarse-grained explanations at a deep layer. LRP and its variants, on the other hand, can generate fine-grained explanations. But the faithfulness of the explanations is too low. To address these challenges, in this paper, we propose FG-CAM (Fine-Grained CAM), which extends CAM-based methods to enable generating fine-grained and high-faithfulness explanations. FG-CAM uses the relationship between two adjacent layers of feature maps with resolution differences to gradually increase the explanation resolution, while finding the contributing pixels and filtering out the pixels that do not contribute. Our method not only solves the shortcoming of CAM-based methods without changing their characteristics, but also generates fine-grained explanations that have higher faithfulness than LRP and its variants. We also present FG-CAM with denoising, which is a variant of FG-CAM and is able to generate less noisy explanations with almost no change in explanation faithfulness. Experimental results show that the performance of FG-CAM is almost unaffected by the explanation resolution. FG-CAM outperforms existing CAM-based methods significantly in both shallow and intermediate layers, and outperforms LRP and its variants significantly in the input layer. Our code is available at https://github.com/dongmo-qcq/FG-CAM.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
