HyperAI
AccueilActualitésArticles de recherche récentsTutorielsEnsembles de donnéesWikiSOTAModèles LLMClassement GPUÉvénements
Recherche
À propos
HyperAI

Visual Place Recognition On Mapillary Val

Métriques

Recall@1
Recall@10
Recall@5

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle
Recall@1
Recall@10
Recall@5
Paper TitleRepository
Conv-AP83.492.390.5GSV-Cities: Toward Appropriate Supervised Visual Place Recognition
Patch-NetVLAD79.587.786.2Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition
NetVLAD (with GPM)82.091.490.4Global Proxy-based Hard Mining for Visual Place Recognition
CosPlace (ResNet-101 2048-D)86.793.492.1Rethinking Visual Geo-localization for Large-Scale Applications
SelaVPR90.897.296.4Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition
ResNeXt GCL + PCA80.992.690.7Generalized Contrastive Optimization of Siamese Networks for Place Recognition
ResNeXt GCL75.588.586.1Generalized Contrastive Optimization of Siamese Networks for Place Recognition
BoQ93.89796.8BoQ: A Place is Worth a Bag of Learnable Queries
CosPlace-91.889.9Rethinking Visual Geo-localization for Large-Scale Applications
DINOv2 SALAD92.29796.4Optimal Transport Aggregation for Visual Place Recognition
Pair-VPR-p95.497.797.3Pair-VPR: Place-Aware Pre-training and Contrastive Pair Classification for Visual Place Recognition with Vision Transformers
MixVPR88.294.393.1MixVPR: Feature Mixing for Visual Place Recognition
BoQ (ResNet-50)91.296.195.3BoQ: A Place is Worth a Bag of Learnable Queries
EffoVPR92.897.497.2EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition-
Pair-VPR-s93.797.397.2Pair-VPR: Place-Aware Pre-training and Contrastive Pair Classification for Visual Place Recognition with Vision Transformers
0 of 15 row(s) selected.