HyperAI超神经
首页资讯最新论文教程数据集百科SOTALLM 模型天梯GPU 天梯顶会
全站搜索
关于
HyperAI超神经

Visual Place Recognition On Pittsburgh 30K

评估指标

Recall@1
Recall@5

评测结果

各个模型在此基准测试上的表现结果

模型名称
Recall@1
Recall@5
Paper TitleRepository
SelaVPR92.897.7Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition
Patch-NetVLAD88.794.5Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition
GCL [trained only on MSLS]81.9494.56Generalized Contrastive Optimization of Siamese Networks for Place Recognition
ProGEO93.098.3ProGEO: Generating Prompts through Image-Text Contrastive Learning for Visual Geo-localization
DINO70.13-Emerging Properties in Self-Supervised Vision Transformers
CosPlace90.45-Rethinking Visual Geo-localization for Large-Scale Applications
CosPlace (ResNet-101 2048-D)90.495.7Rethinking Visual Geo-localization for Large-Scale Applications
SegVLAD-FineT (M)93.1-Revisit Anything: Visual Place Recognition via Image Segment Retrieval
Pair-VPR-p95.497.5Pair-VPR: Place-Aware Pre-training and Contrastive Pair Classification for Visual Place Recognition with Vision Transformers
EigenPlaces92.5-EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition
DINOv278.32-DINOv2: Learning Robust Visual Features without Supervision
MixVPR91.5295.9MixVPR: Feature Mixing for Visual Place Recognition
BoQ93.797.1BoQ: A Place is Worth a Bag of Learnable Queries
Pair-VPR-s94.797.2Pair-VPR: Place-Aware Pre-training and Contrastive Pair Classification for Visual Place Recognition with Vision Transformers
EffoVPR93.997.4EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition-
NetVLAD86.08-NetVLAD: CNN architecture for weakly supervised place recognition
AnyLoc-VLAD-DINOv287.66-AnyLoc: Towards Universal Visual Place Recognition
CLIP54.97-AnyLoc: Towards Universal Visual Place Recognition
BoQ (ResNet-50)92.4-BoQ: A Place is Worth a Bag of Learnable Queries
0 of 19 row(s) selected.