用类星形胶质细胞机制提升ViT模型解释性，更贴近人类感知。
Enhancing Vision Transformer Explainability Using Artificial Astrocytes
- 借鉴神经科学，用人工星形胶质细胞增强预训练ViT推理能力
- 在ClickMe数据集上热力图与人类标注相似度显著提升
- 无需重新训练，适合作为通用解释性增强工具
机器学习模型虽精度高，但决策过程缺乏可解释性，且模型越复杂，可解释性越差。现有方法多依赖新XAI技术或训练时加入约束，适用性有限。本文提出视觉变压器人工星形胶质细胞（ViTA），一种无需训练的解释性增强方法，受神经科学启发，提升预训练深度神经网络的推理能力，生成更符合人类认知的解释。我们采用Grad-CAM和Grad-CAM++两种经典XAI技术评估，对比标准ViT模型。在ClickMe数据集上，通过量化热力图与人类标注（人机对齐）的相似度，结果显示引入人工星形胶质细胞后，所有XAI技术及指标均实现统计显著的性能提升，显著增强了模型解释与人类感知的一致性。
原文摘要 · Abstract (English)
Machine learning models achieve high precision, but their decision-making processes often lack explainability. Furthermore, as model complexity increases, explainability typically decreases. Existing efforts to improve explainability primarily involve developing new eXplainable artificial intelligence (XAI) techniques or incorporating explainability constraints during training. While these approaches yield specific improvements, their applicability remains limited. In this work, we propose the Vision Transformer with artificial Astrocytes (ViTA). This training-free approach is inspired by neuroscience and enhances the reasoning of a pretrained deep neural network to generate more human-aligned explanations. We evaluated our approach employing two well-known XAI techniques, Grad-CAM and Grad-CAM++, and compared it to a standard Vision Transformer (ViT). Using the ClickMe dataset, we quantified the similarity between the heatmaps produced by the XAI techniques and a (human-aligned) ground truth. Our results consistently demonstrate that incorporating artificial astrocytes enhances the alignment of model explanations with human perception, leading to statistically significant improvements across all XAI techniques and metrics utilized.
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。