Individual pet re-identification embeddings (dogs and cats) — the "which pet is this" layer used by Gallery's pet recognition, on top of whole-animal crops from its pet detector.

A frozen facebook/dinov2-large backbone (300M parameters) plus a trained linear projection to 512 dimensions. The projection's L2-normalized output is the embedding; identity is compared with cosine similarity. Fine-tuning the backbone was tried and rejected — it overfits the training identities and forgets DINOv2's general features, while the frozen-backbone projection beats zeroshot on both species.

Crop the detected animal's bounding box, resize to 224x224, normalize with ImageNet statistics (mean [0.485, 0.456, 0.406], std [0.229, 0.224, 0.225]). Compare embeddings with cosine similarity (equivalently, dot product — the outputs are unit vectors).

Verification EER and identification Top-1 on held-out identities — individuals never seen in training — scored over the complete test splits:

The backbone is Apache-2.0. The projection was trained only on openly-licensed data:

DogFaceNet (CC BY) is used for evaluation only. No restrictively-licensed pet re-ID dataset (PetFace, AvitoTech, MegaDescriptor) was used for training or distillation, so this model is safe for commercial use.

pet-recognition-small / pet-recognition-base / pet-recognition-large trade accuracy against cost; base is Gallery's default.