使用人工星形胶质细胞增强Vision Transformer的可解释性
Enhancing Vision Transformer Explainability Using Artificial Astrocytes
AI总结：
提出受神经科学启发的免训练框架ViTA，通过人工星形胶质细胞增强预训练ViT的推理，生成更符合人类感知的解释，在ClickMe数据集上各项XAI指标均获显著提升。
摘要：
机器学习模型实现了高精度，但其决策过程通常缺乏可解释性。此外，随着模型复杂度的增加，可解释性通常会降低。改善可解释性的现有努力主要涉及开发新的可解释人工智能（XAI）技术，或在训练过程中引入可解释性约束。尽管这些方法取得了特定的改进，但其适用性仍然有限。在这项工作中，我们提出了带有人工星形胶质细胞的Vision Transformer（ViTA）。这种免训练方法受神经科学启发，增强了预训练深度神经网络的推理能力，以生成更符合人类认知的解释。我们采用两种著名的XAI技术，即Grad-CAM和Grad-CAM++，对我们的方法进行了评估，并将其与标准的Vision Transformer（ViT）进行了比较。使用ClickMe数据集，我们量化了XAI技术生成的热图与（符合人类认知的）真实标签之间的相似度。我们的结果一致表明，引入人工星形胶质细胞增强了模型解释与人类感知的契合度，在所有使用的XAI技术和指标上都带来了统计学上的显著改善。
英文摘要：
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.
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。
