对比解释AI方法，帮你在不同场景选对工具。
A Comparative Study of Explainable AI Methods: Model-Agnostic vs. Model-Specific Approaches
- 分模型无关与特定方法，比较解释效果差异。
- 模型无关法适用广，特定方法更准且快。
- 多方法结合最可靠，适合医疗自动驾驶等高风险领域。
本文比较了深度学习图像分类中模型无关与模型特定的可解释AI（XAI）方法。通过在不同类别图像（如狗、鸟、昆虫）上测试ResNet50的预测，分析LIME和SHAP（模型无关方法）与Grad-CAM及Guided Backpropagation（模型特定方法）的表现。结果表明，每种方法揭示了模型决策过程的不同方面：模型无关方法提供跨架构的广泛特征归因，而模型特定方法在精准定位激活区域上表现更优，且计算效率更高。研究显示不存在通用的可解释方案，结合多种方法能获得最全面的理解，尤其适用于医疗、自动驾驶和金融等对透明度要求高的领域。该对比框架为根据具体需求和算力限制选择合适解释技术提供了实践指导。
原文摘要 · Abstract (English)
This paper compares model-agnostic and model-specific approaches to explainable AI (XAI) in deep learning image classification. I examine how LIME and SHAP (model-agnostic methods) differ from Grad-CAM and Guided Backpropagation (model-specific methods) when interpreting ResNet50 predictions across diverse image categories. Through extensive testing with various species from dogs and birds to insects I found that each method reveals different aspects of the models decision-making process. Model-agnostic techniques provide broader feature attribution that works across different architectures, while model-specific approaches excel at highlighting precise activation regions with greater computational efficiency. My analysis shows there is no "one-size-fits-all" solution for model interpretability. Instead, combining multiple XAI methods offers the most comprehensive understanding of complex models particularly valuable in high-stakes domains like healthcare, autonomous vehicles, and financial services where transparency is crucial. This comparative framework provides practical guidance for selecting appropriate interpretability techniques based on specific application needs and computational constraints.
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。