Research map / Label-efficient and robust learning / Recognition and long-tail
SAGE: Spatial-visual Adaptive Graph Exploration for Efficient Visual Place Recognition
Shunpeng Chen, Changwei Wang, Rongtao Xu, Peixingtian, yukun Song, Jinzhou Lin, Wenhao Xu, jingyizhang, Li Guo, Shibiao Xu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Soft Probing in place of CFP aggregation (ablation) | SAGE-B (OGC+GWS) · Nordland | Recall@1: 95.4 -> 95.8 | Improved |
| add Soft Probing in place of CFP aggregation (ablation) | SAGE-B (OGC+GWS) · SPED | Recall@1: 97.5 -> 98.0 | Improved |
| add Online Graph Creation to SoftP+GWS (ablation) | SAGE-B · Nordland | Recall@1: 94.2 -> 95.8 | Improved |
| add Greedy Weighted Sampling to SoftP+OGC (ablation) | SAGE-B · Nordland | Recall@1: 95.2 -> 95.8 | Improved |
| add Greedy Weighted Sampling to SoftP+OGC (ablation) | SAGE-B · MSLS-val | Recall@1: 93.6 -> 94.3 | Improved |
| online graph rebuilt each epoch vs offline mining (ablation) | SAGE · SPED | Recall@1: 98.5 -> 98.9 | Improved |
| online graph rebuilt each epoch vs offline mining (ablation) | SAGE · MSLS-val | Recall@1: 94.2 -> 94.5 | Improved |
| use GWS instead of Cliquemining (ablation) | SAGE (online) · SPED | Recall@1: 90.0 -> 98.9 | Improved |
| dynamic sampling vs Cliquemining, early training (ablation) | SAGE · MSLS-val epoch 4 | Recall@1: 92.7 -> 93.4 | Improved |
| enlarge InteractHead feed-forward dim from 1024 to 1536 (ablation) | SAGE · SPED / Pitts30k | Recall@1: SPED 98.9 -> 98.6; Pitts30k 95.8 -> 96.0 | Mixed |
| add InteractHead cross-image encoder (ablation) | SAGE-B · SPED | Recall@1: 91.8 -> 98.9 | Improved |
| fine-tune with frozen backbone and DPN | SAGE · trainable parameters (M) | trainable params: 29.8 -> 1.96 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SuperVLAD — SuperVLAD: Compact and Robust Image Descriptors for Visual Place Recognition (NeurIPS 2024) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition (AAAI 2025 · similarity 0.92)
- MutualVPR: A Mutual Learning Framework for Resolving Supervision Inconsistencies via Adaptive Clustering (NeurIPS 2025 · similarity 0.91)
- Towards Implicit Aggregation: Robust Image Representation for Place Recognition in the Transformer Era (NeurIPS 2025 · similarity 0.90)
- Optimal Transport Aggregation for Visual Place Recognition (CVPR 2024 · similarity 0.90)
- Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition (ICLR 2024 · similarity 0.89)
- EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition (ICLR 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
