让嵌入空间的相似性可解释，看清哪些特征决定图像或图文间的远近。
Explainable embeddings with Distance Explainer
- 用掩码筛选+距离排序，给嵌入点间距离分配贡献度
- 在ImageNet和CLIP上验证，解释结果忠实且稳定
- 适合需要理解嵌入空间决策机制的研究者
尽管可解释人工智能（XAI）已取得显著进展，但很少有方法能解释嵌入向量空间中维度所代表的复杂抽象。我们提出Distance Explainer，一种用于生成机器学习模型嵌入空间局部后验解释的新方法。该方法将基于显著性的技术（如RISE） adapted 以解释两个嵌入数据点之间的距离，通过选择性掩码和距离排序的掩码过滤来分配归因值。我们在跨模态嵌入（图像-图像和图像-文本对）上评估该方法，采用经典的XAI指标：忠实性、敏感性/鲁棒性和随机化测试。使用ImageNet和CLIP模型的实验表明，该方法能有效识别影响数据点间相似性或差异性的特征，同时保持高鲁棒性和一致性。我们还研究了参数调优（特别是掩码数量和选择策略）对解释质量的影响。这项工作填补了XAI研究中的关键空白，提升了深度学习应用中嵌入空间的透明度与可信度。
原文摘要 · Abstract (English)
While eXplainable AI (XAI) has advanced significantly, few methods address interpretability in embedded vector spaces where dimensions represent complex abstractions. We introduce Distance Explainer, a novel method for generating local, post-hoc explanations of embedded spaces in machine learning models. Our approach adapts saliency-based techniques from RISE to explain the distance between two embedded data points by assigning attribution values through selective masking and distance-ranked mask filtering. We evaluate Distance Explainer on cross-modal embeddings (image-image and image-caption pairs) using established XAI metrics including Faithfulness, Sensitivity/Robustness, and Randomization. Experiments with ImageNet and CLIP models demonstrate that our method effectively identifies features contributing to similarity or dissimilarity between embedded data points while maintaining high robustness and consistency. We also explore how parameter tuning, particularly mask quantity and selection strategy, affects explanation quality. This work addresses a critical gap in XAI research and enhances transparency and trustworthiness in deep learning applications utilizing embedded spaces.
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。