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

The study investigates whether Vision Transformer (ViT)-based animal re-identification models learn biologically meaningful concepts. Using a DINOv3 backbone fine‑tuned on Western lowland gorilla images, the authors find that sex and age emerge as linear directions in the model’s representations, generalizing to unseen individuals with high AUROC scores. They demonstrate that the sex direction is causally used by the model, that fine‑tuning relocates these concepts within the network, and that the representations reflect a graded biological axis encoded redundantly across the population.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• computer-vision
• fine-tuning
• safety