metadata
license: mit
tags:
- visual-place-recognition
- image-retrieval
- image-feature-extraction
- pytorch
- dinov2
pipeline_tag: image-feature-extraction
library_name: pytorch
SAGE-VPR
Official checkpoints for SAGE: Spatial-visual Adaptive Graph Exploration for Efficient Visual Place Recognition.
Paper: https://arxiv.org/abs/2509.25723
GitHub: https://github.com/chenshunpeng/SAGE
Project Page: https://chenshunpeng.github.io/projects/SAGE
Checkpoints
| File | Description |
|---|---|
SAGE.pth |
Full SAGE checkpoint with the cross-image encoder. |
SAGE_No-Encoder_Vit-B.pth |
SAGE checkpoint without the cross-image encoder, using DINOv2 ViT-B as the backbone. |
SAGE_No-Encoder_Vit-L.pth |
SAGE checkpoint without the cross-image encoder, using DINOv2 ViT-L as the backbone. |