Metraipolis › archive › dc_8db7d119d199

What Does Animal Re-Identification Learn? Linear Biological Concepts and Their Origins in Visual Representations — arXiv:2609.06020

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.06020
License (as archived)
CC0-1.0
Archived
2026-10-16T15:06:47.399Z
SHA-256 of the archived text
52862ab08aab7f2bd54d4192db2489a952a1a67f8d738c299949b0f67c3e1207
Stable URL of this page
https://metraipolis.com/documento/dc_8db7d119d199

How to cite

What Does Animal Re-Identification Learn? Linear Biological Concepts and Their Origins in Visual Representations — arXiv:2609.06020 — arXiv (en), https://arxiv.org/abs/2609.06020 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8db7d119d199 (Metraipolis archive dc_8db7d119d199, sha256 52862ab08aab7f2bd54d4192db2489a952a1a67f8d738c299949b0f67c3e1207)
BibTeX
@misc{dc8db7d119d199,
  title = {What Does Animal Re-Identification Learn? Linear Biological Concepts and Their Origins in Visual Representations — arXiv:2609.06020},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.06020},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8db7d119d199; sha256 52862ab08aab7f2bd54d4192db2489a952a1a67f8d738c299949b0f67c3e1207},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06020. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Conservation increasingly relies on camera traps that collect more wildlife imagery than experts can manually analyze, making animal re-identification (Re-ID) essential for monitoring individuals and populations. Yet understanding which cues drive model decisions is challenging for ViT-based Re-ID models, whose metric-learning objectives provide no explicit supervision for biological concepts. We ask whether such models nonetheless organize their representations along biologically meaningful axes. Using a DINOv3 backbone fine-tuned for Western lowland gorilla Re-ID with triplet-margin loss, we find that sex and age emerge as linear directions that generalize to held-out individuals, reaching up to 0.91 AUROC and being recoverable from a single image per individual. Activation steering further shows that the sex direction is causally used by the model, flipping a significant fraction of predictions to the opposite sex. Comparing off-the-shelf and fine-tuned backbones shows that Re-ID training does not create these concepts, but relocates them across the network. Finally, data attribution reveals that the representation we find reflects a graded biological axis, is redundantly encoded across the population and shaped by visually ambiguous individuals. Together, these findings show how interpretability can uncover both the biological structure and failure modes of Re-ID representations, providing a step toward auditable computer vision for wildlife monitoring.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.06020 — 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 2026-10-16T14:49:57.038Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).