In the ever-evolving field of Artificial Intelligence, a critical challenge has been to decipher the decision-making processes within the so-called "black boxes" in deep learning. Over recent years, a plethora of methods have emerged, dedicated to explaining decisions across diverse tasks. Particularly in tasks like image classification, these methods typically identify and emphasize the pivotal pixels that most influence a classifier's prediction. Interestingly, this approach mirrors human behavior: when asked to explain our rationale for classifying an image, we often point to the most salient features or aspects. Capitalizing on this parallel, our research embarked on a user-centric study. We sought to objectively measure the interpretability of three leading explanation methods: (1) Prototypical Part Network, (2) Occlusion, and (3) Layer-wise Relevance Propagation. Intriguingly, our results highlight that while the regions spotlighted by these methods can vary widely, they all offer humans a nearly equivalent depth of understanding. This enables users to discern and categorize images efficiently, reinforcing the value of these methods in enhancing AI transparency.

翻译：在不断发展的人工智能领域中，一个关键挑战是如何解读深度学习所谓的"黑箱"中的决策过程。近年来，涌现出大量致力于解释各类任务决策的方法。特别是在图像分类等任务中，这些方法通常会识别并强调对分类器预测影响最大的关键像素。有趣的是，这种方法与人类行为相契合：当我们被要求解释对图像分类的推理过程时，往往会指出最显著的特征或方面。基于这一相似性，我们的研究开展了一项以用户为中心的研究。我们旨在客观衡量三种主流解释方法的可解释性：（1）原型部分网络（Prototypical Part Network）、（2）遮挡法（Occlusion）、（3）逐层相关性传播（Layer-wise Relevance Propagation）。引人注目的是，我们的结果表明，尽管这些方法强调的区域可能存在显著差异，但它们都能为人类提供近乎同等的理解深度。这使得用户能够高效地识别和分类图像，从而强化了这些方法在增强人工智能透明度方面的价值。