| --- |
| license: apache-2.0 |
| pipeline_tag: image-feature-extraction |
| tags: |
| - pet-re-identification |
| - image-embeddings |
| - onnx |
| - dinov2 |
| library_name: onnx |
| --- |
| |
| # pet-recognition-base |
|
|
| Individual **pet re-identification** embeddings (dogs and cats) — the "which pet is this" |
| layer used by [Gallery](https://opennoodle.de)'s pet recognition, on top of whole-animal |
| crops from its pet detector. |
|
|
| A **frozen [`facebook/dinov2-base`](https://huggingface.co/facebook/dinov2-base)** backbone (86M |
| 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. |
|
|
| ## I/O contract |
|
|
| | | | |
| | --- | --- | |
| | Input | `input`, float32 `[N, 3, 224, 224]`, RGB, ImageNet mean/std normalized | |
| | Output | `embedding`, float32 `[N, 512]`, **L2-normalized** | |
| | Batch | dynamic | |
| | Opset | 17 | |
|
|
| 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). |
|
|
| ## Quality |
|
|
| Verification EER and identification Top-1 on **held-out identities** — individuals never |
| seen in training — scored over the complete test splits: |
|
|
| | Test set | Images | Identities | EER | Top-1 | AUC | |
| | --- | --- | --- | --- | --- | --- | |
| | Dogs — Dogs-World (whole animal) | 53830 | 16469 | 0.047 | 0.612 | 0.988 | |
| | Cats — Cat Individual Images (whole animal) | 2575 | 102 | 0.045 | 0.916 | 0.991 | |
| | Dogs — DogFaceNet (unseen dataset, aligned faces) | 8363 | 1393 | 0.031 | 0.943 | 0.994 | |
|
|
| ## Training data & licensing |
|
|
| The backbone is Apache-2.0. The projection was trained **only** on openly-licensed data: |
|
|
| - **Dogs-World** (CC0) — whole-animal dog photos, identity from the per-image metadata |
| sidecars; single-dog images only. |
| - **Cat Individual Images** (CC BY) — whole-animal cat photos, one directory per cat. |
|
|
| 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. |
|
|
| ## Siblings |
|
|
| `pet-recognition-small` / `pet-recognition-base` / `pet-recognition-large` trade accuracy |
| against cost; `base` is Gallery's default. |
|
|
