Det-LIME: Detector-Aware, Multi-Instance Local Interpretable Model-Agnostic Explanations for Automated Marine Mammal Detection
Det-LIME extends LIME to multi-instance object detection explanations, improving attribution for harbor seal aerial surveys.
Det-LIME adapts LIME to object detection by combining per-detection weighting, a proximity kernel emphasizing box-adjacent regions, and IoU-based matching to track instances across perturbations. It was evaluated on aerial drone imagery for harbor seal detection plus a seabird case study, and compared against vanilla LIME, Stabilized LIME, Deterministic LIME, and gradient-based attribution. Using Attribution Ratio and Max Saliency Hit Rate metrics, it consistently improved multi-instance attribution and produced box-aligned explanations useful for debugging and data augmentation.
- Multi-instance LIME variant produces box-aligned, per-detection explanations for object detectors
- Combines per-detection weighting, proximity kernel, and IoU-based instance tracking
- Outperforms vanilla, Stabilized, and Deterministic LIME on attribution metrics
- Validated on harbor seal drone imagery and a seabird case study
From the original article
1 min read at arxiv.orgDespite the rapid uptake of black-box object detectors in marine mammal research and monitoring, explainability techniques are rarely integrated into conservation workflows.
By Jiayi Zhou · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.