Metraipolis › archive › dc_4e1c2d8f1683

Det-LIME: Detector-Aware, Multi-Instance Local Interpretable Model-Agnostic Explanations for Automated Marine Mammal Detection — arXiv:2609.17479

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.17479
License (as archived)
CC0-1.0
Archived
2026-10-15T18:38:59.691Z
SHA-256 of the archived text
6f0633d59a86c14f7f812397dae75b3f2b95ae5777394960e16d44dd6ee29911
Stable URL of this page
https://metraipolis.com/documento/dc_4e1c2d8f1683

How to cite

Det-LIME: Detector-Aware, Multi-Instance Local Interpretable Model-Agnostic Explanations for Automated Marine Mammal Detection — arXiv:2609.17479 — arXiv (en), https://arxiv.org/abs/2609.17479 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4e1c2d8f1683 (Metraipolis archive dc_4e1c2d8f1683, sha256 6f0633d59a86c14f7f812397dae75b3f2b95ae5777394960e16d44dd6ee29911)
BibTeX
@misc{dc4e1c2d8f1683,
  title = {Det-LIME: Detector-Aware, Multi-Instance Local Interpretable Model-Agnostic Explanations for Automated Marine Mammal Detection — arXiv:2609.17479},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.17479},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4e1c2d8f1683; sha256 6f0633d59a86c14f7f812397dae75b3f2b95ae5777394960e16d44dd6ee29911},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17479. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.17479 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T18:03:09.762Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).