Skip to content
ModelListedExternal
Download

Cat Reid Dinov3

Fine-tuned DINOv3 ViT-B/16 for cat re-identification.

KindOtherVersionFinetuned bestCgrade

Model source

Kind
Other
File size
328 MB
Version
vFinetuned best
Updated
Oct 10, 2026
Source
Hugging Face

Source description

Cat ReID — DINOv3 Fine-tuned

Fine-tuned DINOv3 ViT-B/16 for cat re-identification.

Usage

import torch
from ai.feature_extractor import VisionFeatureExtractor

extractor = VisionFeatureExtractor(device="cpu", checkpoint="finetuned_best.pt")
feature = extractor.extract(image)  # 256-dim normalized embedding

Model

  • Backbone: DINOv3 ViT-B/16 (768-dim)
  • Head: Linear(768 → 256) + L2-norm
  • Training: Triplet margin loss with batch-hard mining
  • Classes: 131 cats

Sources

1 source
Hugging FacePrimaryVersion fefdd206f2a77ef7247ca583e5604441e5b3259f
huggingface.co/theavenger/cat-reid-dinov3/tree/fefdd206f2a77ef7247ca583e5604441e5b3259f

Verified Oct 10

Model artifacts

1 artifact

finetuned_best.pt

pt · 328 MB · SHA-256 32f04b89e7f2…eb6e · Hugging Face

Download file

Source excerpts

2 excerpts

--- license: mit tags: - re-identification - metric-learning - cat - dinov3 - pytorch pipeline_tag: image-feature-extraction --- # Cat ReID — DINOv3 Fine-tuned Fine-tuned [DINOv3 ViT-B/16](https://huggingface.co/timm/vit_base_patch16_dinov3.lvd1689m) for cat re-identification. ## Usage ```python import torch from ai.feature_extractor import VisionFeatureExtractor extractor = VisionFeatureExtractor(device="cpu", checkpoint="finetuned_best.pt") feature = extractor.extract(image) # 256-dim normalized embedding ``` ## Model - **Backbone**: DINOv3 ViT-B/16 (768-dim) - **Head**: Linear(768 → 256) + L2-norm - **Training**: Triplet margin loss with batch-hard mining - **Classes**: 131 cats

Source context: 0 downloads · 0 likes · Pipeline image-feature-extraction · Repo theavenger/cat-reid-dinov3