发表机构
Missouri State University（密苏里州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
MOXIE是一种进化框架，通过多目标搜索生成替代解释的帕累托前沿，在保持分类器置信度的同时最小化图像保留量，在多个数据集上优于LIME，提供更全面的决策视图。
AI 中文摘要
基于分割的解释方法（如LIME）为每个预测返回一个单一的解释，该解释是根据一个固定的图像分割计算得出的。这掩盖了两个重要事实：一个预测可以由许多不同的图像分割子集支持，并且分割本身会影响可以找到哪些解释。我们引入了MOXIE（多目标解释成像引擎），这是一个进化框架，用于搜索在尽可能保留较少图像的同时保持分类器置信度的分割子集。MOXIE不是返回一个解释，而是返回一个替代解释的帕累托前沿，范围从紧凑到高度忠实。我们使用NSGA-II和四种分割方法（SLIC、Felzenszwalb、Watershed和Voronoi）在BloodMNIST和HAM10000数据集上评估MOXIE，使用与LIME相同的评估预算。结果表明，MOXIE在每张图像上都比LIME实现了更高的超体积。LIME的解释通常看起来令人信服，但当仅显示高亮分割时，分类器的置信度会崩溃。MOXIE的前沿揭示了需要多少图像来保持模型的置信度，以及哪些上下文区域影响它。我们还发现分割强烈影响评估：当分割被计数时，具有不等分割大小的方法看起来最紧凑。这些结果表明，替代解释比单一解释提供了对模型决策更全面的视图。
英文摘要
Segment-based explanation methods such as LIME return a single explanation for each prediction, computed from one fixed image segmentation. This hides two important facts: a prediction can be supported by many different sets of image segments, and the segmentation itself shapes which explanations can be found. We introduce MOXIE (Multi-Objective eXplanation Imaging Engine), an evolutionary framework that searches for segment subsets that preserve the classifier's confidence while keeping as little of the image as possible. Instead of one explanation, MOXIE returns a Pareto front of alternative explanations that range from compact to highly faithful. We evaluate MOXIE with NSGA-II and four segmentation methods (SLIC, Felzenszwalb, Watershed and Voronoi) on BloodMNIST and HAM10000 datasets, using the same evaluation budget as LIME. Results show that MOXIE achieves a higher hypervolume than LIME on every image. LIME's explanations often appear convincing, yet the classifier's confidence collapses when only the highlighted segments are shown. MOXIE's fronts reveal how much of the image is needed to preserve the model's confidence and which contextual regions influence it. We also find that segmentation strongly affects evaluation: methods with unequal segment sizes appear most compact when segments are counted. These results show that alternative explanations provide a more complete view of a model's decision than a single explanation.
