通过语义区域稀疏化，让模型决策过程更可解释。
From Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature Selection
- 在语义像素区域而非像素级进行遮蔽，贴近人类感知
- 动态调整每张图像的稀疏程度，提升解释一致性
- 在合成与自然图像上优于现有方法，结果更符合人理解
理解机器学习模型的决策过程，有助于洞察任务本质、数据特性以及模型失败原因。本文提出一种通过实例级输入图像稀疏化实现内在可解释预测的方法。为使稀疏化更贴近人类感知，我们在语义有意义的像素区域空间中学习掩码，而非像素级别。此外，我们引入一种显式机制，动态确定每个实例所需的稀疏度。在半合成和自然图像数据集上的实验证明，该可解释分类器产生的预测比当前最优基准更具意义且更易被人理解。
原文摘要 · Abstract (English)
Understanding the decision-making process of machine learning models provides valuable insights into the task, the data, and the reasons behind a model's failures. In this work, we propose a method that performs inherently interpretable predictions through the instance-wise sparsification of input images. To align the sparsification with human perception, we learn the masking in the space of semantically meaningful pixel regions rather than on pixel-level. Additionally, we introduce an explicit way to dynamically determine the required level of sparsity for each instance. We show empirically on semi-synthetic and natural image datasets that our inherently interpretable classifier produces more meaningful, human-understandable predictions than state-of-the-art benchmarks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。