通过语义深度分析，揭示视觉模型误判背后的内在原因。
Semantic Depth Matters: Explaining Errors of Deep Vision Networks through Perceived Class Similarities
- 用类模板提取网络感知的语义层级结构
- 发现高语义深度使错误更符合真实相似性
- 无需重训练，适合已部署模型的可解释性分析
理解深度神经网络（DNN）行为不能仅依赖分类准确率，分析其错误及其可预测性同样关键。现有评估方法缺乏透明度，难以解释模型误判的根本原因。为此，我们提出一个新框架，研究网络感知的语义层级深度与其真实数据误判模式之间的关系。核心是引入相似度深度（Similarity Depth, SD）度量，量化网络内部感知的语义层级深度，并评估其错误与内部感知相似性结构的匹配程度。我们还提出基于图的模型语义关系与误判可视化方法。该方法利用类模板——由分类器层权重导出的表示——适用于已训练网络，无需额外数据或实验。结果表明，深度视觉网络编码了特定语义层次，且更高的语义深度能提升感知相似性与实际错误的一致性。
原文摘要 · Abstract (English)
Understanding deep neural network (DNN) behavior requires more than evaluating classification accuracy alone; analyzing errors and their predictability is equally crucial. Current evaluation methodologies lack transparency, particularly in explaining the underlying causes of network misclassifications. To address this, we introduce a novel framework that investigates the relationship between the semantic hierarchy depth perceived by a network and its real-data misclassification patterns. Central to our framework is the Similarity Depth (SD) metric, which quantifies the semantic hierarchy depth perceived by a network along with a method of evaluation of how closely the network's errors align with its internally perceived similarity structure. We also propose a graph-based visualization of model semantic relationships and misperceptions. A key advantage of our approach is that leveraging class templates -- representations derived from classifier layer weights -- is applicable to already trained networks without requiring additional data or experiments. Our approach reveals that deep vision networks encode specific semantic hierarchies and that high semantic depth improves the compliance between perceived class similarities and actual errors.
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。