Det-LIME：面向自动化海洋哺乳动物检测的检测器感知、多实例局部可解释模型无关解释
Det-LIME: Detector-Aware, Multi-Instance Local Interpretable Model-Agnostic Explanations for Automated Marine Mammal Detection
浏览论文内容
中文总结 AI 辅助
Det-LIME通过检测器感知的多实例LIME方法，为海洋哺乳动物检测提供框对齐的实例级解释，显著提升多实例归因性能，支持调试与数据优化。
中文摘要 AI 辅助
尽管黑盒目标检测器在海洋哺乳动物研究和监测中被迅速采用，但可解释性技术很少被整合到保护工作流程中。此外，大多数面向分类的可解释性工具不适合涉及社会性生物或具有群体生活史的生物的检测任务，因为它们忽略场景中的多个检测结果，并产生单实例输出，模糊了个体间的证据。这些方法还生成低分辨率、通常生物学上无关的视觉内容，限制了其在调试、定向数据增强和精细化数据收集中的实用性。我们提出了Det-LIME，一种检测器感知的、多实例适应的局部可解释模型无关解释（LIME），通过结合逐检测加权、强调每个框附近区域的邻近核以及基于交并比的匹配来跟踪扰动中的同一实例，从而生成实例特定、框对齐的解释。我们在用于港海豹检测的航空无人机图像上评估了Det-LIME，并附加了一个海鸟案例研究以评估泛化性，同时将其与原始LIME、稳定LIME、确定性LIME和基于梯度的归因方法进行了比较。使用归因比率和最大显著性命中率指标，我们表明Det-LIME持续改善了多实例归因。在实践中，这些更高分辨率、实例感知的解释提供了对模型输出的洞察，并支持后处理、调试以及建模和数据收集或增强中的可操作改进。
英文摘要
Despite the rapid uptake of black-box object detectors in marine mammal research and monitoring, explainability techniques are rarely integrated into conservation workflows. Furthermore, most classification-oriented explainability tools are ill-suited to detection tasks involving imagery of social organisms or those with colonial life histories, as they ignore multiple detections within a scene and produce single-instance outputs that blur evidence across individuals. These methods also generate low-resolution, often biologically irrelevant visuals, limiting their utility for debugging, targeted data augmentation, and refined data collection. We proposed Det-LIME, a detector-aware, multi-instance adaptation of Local Interpretable Model-Agnostic Explanations (LIME) that produced instance-specific, box-aligned explanations by combining per-detection weighting, a proximity kernel that emphasizes regions near each box, and Intersection-over-Union-based matching to track the same instance across perturbations. We evaluated Det-LIME on aerial drone imagery for harbor seal detection, with an additional seabird case study to assess generality, and compared it with vanilla LIME, Stabilized LIME, Deterministic LIME, and gradient-based attribution methods. Using the Attribution Ratio and Max Saliency Hit Rate metrics, we showed that Det-LIME consistently improved multi-instance attribution. In practice, these higher-resolution, instance-aware explanations provide insight into model outputs and support post-processing, debugging, and actionable improvements in modeling and data collection or augmentation.
发表机构
- Duke University（杜克大学）
机构由 AI 辅助整理，请以论文原文为准。
