AI Paper Atlas

Research map / Benchmarks / Pitts250k

Pitts250k leaderboard

12 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Pitts250k. Best R@1: 97.3 (A2GC (33280, ViTg), CVPR 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

Pitts250k · R@1

12 papers, each with its best reported number for its own method; higher is better.

#R@1 ↑MethodPaperTopic
197.3A2GC (33280, ViTg)
DINOv2 ViT-g/14
A2GC: Asymmetric Aggregation with Geometric Constraints for Locally Aggregated Descriptors
CVPR 2026 · Table 1
Recognition and long-tail
297FoL-re-ranking
DINOv2 ViT-L
Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition
AAAI 2025 · Table 1
CNN features
396.5ImAge*
DINOv2-base-register
Towards Implicit Aggregation: Robust Image Representation for Place Recognition in the Transformer Era
NeurIPS 2025 · Table 3
Attention and transformers
496.5EMVP-L
DINOv2 ViT-L
EMVP: Embracing Visual Foundation Model for Visual Place Recognition with Centroid-Free Probing
NeurIPS 2024 · Table 1(a)
Human and embodied modeling
595.7SelaVPR
DINOv2 ViT-L/14
Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition
ICLR 2024 · Appendix Table
Human and embodied modeling
695.6VLAD-BuFF w. PCAW (8K)
DINOv2 ViT-B
VLAD-BuFF: Burst-aware Fast Feature Aggregation for Visual Place Recognition
ECCV 2024 · Table 1
Recognition and long-tail
795.4EfficientVPR
DINOv2-S
EfficientVPR: Toward Efficient Visual Place Recognition via Scene-Aware Prompt Tuning and Adaptive Feature Enhancement
CVPR 2026 · Table 1
Recognition and long-tail
895.2DINOv2 SALAD + CliqueMining
DINOv2 SALAD
"Close, But Not There: Boosting Geographic Distance Sensitivity in Visual Place Recognition"
ECCV 2024 · Table 1
Recognition and long-tail
995.1DINOv2 SALAD
DINOv2-B
Optimal Transport Aggregation for Visual Place Recognition
CVPR 2024 · Table 1
Recognition and long-tail
1095BoQ (Ours)
ResNet-50
BoQ: A Place is Worth a Bag of Learnable Queries
CVPR 2024 · Table 2
Attention and transformers
2 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.