让深度模型的解释有名字又准确，不改模型也能做到。
Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation
- 用大语言模型生成概念名，再用CLIP定位图像区域，实现命名与忠实解释统一。
- 在自然图像、场景和医学影像上，解释既精准又对决策关键，插入/删除概念时表现稳定。
- 无需重训模型，适合需要可解释性但不能动模型的高风险场景。
深度神经网络广泛应用于高风险视觉任务，可解释性至关重要，但现有方法存在权衡：后处理概念方法虽忠实于模型行为，却无名称；命名且设计导向的方法需重训练或修改分类器。我们提出语言锚定分解（LAD），一种无需修改模型的后处理框架，可同时获得命名、忠实且不依赖重训练的概念。对每个类别，大语言模型生成概念词汇，基于CLIP的相似性图将这些概念定位到图像区域。通过反向标准非负矩阵分解，LAD将这些语言引导的图固定为系数矩阵，仅学习能重建冻结编码器激活的概念基，使命名成为结构约束，模型自身的特征几何决定保留哪些概念。移除该锚点虽保持精度，但解释忠实度崩溃。在自然图像、场景和医学影像基准测试中，LAD生成空间精确的解释，在概念插入与删除下仍具决策相关性，且唯一提供稳定、人类可读的概念名称。
原文摘要 · Abstract (English)
Deep neural networks are widely deployed in high-stakes visual applications where interpretability is critical, yet existing explanations face a trade-off: post-hoc concept methods recover factors that are faithful to a model's behavior but unnamed, while naming and by-design methods attach human-readable concepts only by retraining or altering the classifier. We propose Language-Anchored Decomposition (LAD), a post-hoc framework that delivers concepts which are simultaneously named, faithful, and obtained without modifying the model. For each class, a large language model proposes a concept vocabulary that CLIP-based similarity maps localize across image regions. Inverting standard non-negative matrix factorization, LAD fixes these language-grounded maps as the coefficient matrix and learns only a concept basis that reconstructs the frozen encoder's activations, so naming becomes a structural constraint and the model's own feature geometry determines which concepts are retained. Removing this anchor preserves accuracy but collapses attribution faithfulness. Across natural-image, scene, and medical-imaging benchmarks, LAD produces spatially precise explanations that are decision-relevant under both concept insertion and deletion, while uniquely providing stable, human-interpretable concept names.
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。