SAGE: Spatial-visual Adaptive Graph Exploration for Efficient Visual Place Recognition
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912919011196928 |
|---|---|
| author | Chen, Shunpeng Wang, Changwei Xu, Rongtao Pei, Xingtian Song, Yukun Lin, Jinzhou Xu, Wenhao Zhang, Jingyi Guo, Li Xu, Shibiao |
| author_facet | Chen, Shunpeng Wang, Changwei Xu, Rongtao Pei, Xingtian Song, Yukun Lin, Jinzhou Xu, Wenhao Zhang, Jingyi Guo, Li Xu, Shibiao |
| contents | Visual Place Recognition (VPR) requires robust retrieval of geotagged images despite large appearance, viewpoint, and environmental variation. Prior methods focus on descriptor fine-tuning or fixed sampling strategies yet neglect the dynamic interplay between spatial context and visual similarity during training. We present SAGE (Spatial-visual Adaptive Graph Exploration), a unified training pipeline that enhances granular spatial-visual discrimination by jointly improving local feature aggregation, organize samples during training, and hard sample mining. We introduce a lightweight Soft Probing module that learns residual weights from training data for patch descriptors before bilinear aggregation, boosting distinctive local cues. During training we reconstruct an online geo-visual graph that fuses geographic proximity and current visual similarity so that candidate neighborhoods reflect the evolving embedding landscape. To concentrate learning on the most informative place neighborhoods, we seed clusters from high-affinity anchors and iteratively expand them with a greedy weighted clique expansion sampler. Implemented with a frozen DINOv2 backbone and parameter-efficient fine-tuning, SAGE achieves SOTA across eight benchmarks. Notably, our method obtains 100% Recall@10 on SPED only using 4096D global descriptors. The code and model are available at https://github.com/chenshunpeng/SAGE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_25723 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SAGE: Spatial-visual Adaptive Graph Exploration for Efficient Visual Place Recognition Chen, Shunpeng Wang, Changwei Xu, Rongtao Pei, Xingtian Song, Yukun Lin, Jinzhou Xu, Wenhao Zhang, Jingyi Guo, Li Xu, Shibiao Computer Vision and Pattern Recognition Visual Place Recognition (VPR) requires robust retrieval of geotagged images despite large appearance, viewpoint, and environmental variation. Prior methods focus on descriptor fine-tuning or fixed sampling strategies yet neglect the dynamic interplay between spatial context and visual similarity during training. We present SAGE (Spatial-visual Adaptive Graph Exploration), a unified training pipeline that enhances granular spatial-visual discrimination by jointly improving local feature aggregation, organize samples during training, and hard sample mining. We introduce a lightweight Soft Probing module that learns residual weights from training data for patch descriptors before bilinear aggregation, boosting distinctive local cues. During training we reconstruct an online geo-visual graph that fuses geographic proximity and current visual similarity so that candidate neighborhoods reflect the evolving embedding landscape. To concentrate learning on the most informative place neighborhoods, we seed clusters from high-affinity anchors and iteratively expand them with a greedy weighted clique expansion sampler. Implemented with a frozen DINOv2 backbone and parameter-efficient fine-tuning, SAGE achieves SOTA across eight benchmarks. Notably, our method obtains 100% Recall@10 on SPED only using 4096D global descriptors. The code and model are available at https://github.com/chenshunpeng/SAGE. |
| title | SAGE: Spatial-visual Adaptive Graph Exploration for Efficient Visual Place Recognition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.25723 |