Image Retrieval on Revisited Paris (RPar) Medium 1.0 (test)
86.7mAPDELG + RRT
Evaluation results
| Method | Links | ||
|---|---|---|---|
| DELG + RRTTraining set=GLDv2-clean, Net=ResNet-50, Number of local descriptors=500, Feature Type=Global features + Re-ranking2021.03 | 86.7 | 69.8 | |
| DELG + GVTraining set=GLDv2-clean, Net=ResNet-50, Number of local descriptors=1000, Feature Type=Global features + Re-ranking2021.03 | 85.7 | 69.6 | |
| DELG + RRTTraining set=GLDv1&v2-clean, Net=ResNet-50, Number of local descriptors=500, Feature Type=Global features + Re-ranking2021.03 | 82.7 | 60.7 | |
| DELG + GVTraining set=GLDv1, Net=ResNet-50, Number of local descriptors=1000, Feature Type=Global features + Re-ranking2021.03 | 82.3 | 60.5 | |
| DELGTraining set=GLDv1, Net=ResNet-50, Number of local descriptors=0, Feature Type=Global features2021.03 | 81.6 | 59.7 | |
| HOW-ASMKTraining set=SfM-120k, Net=ResNet-50, Number of local descriptors=2000, Feature Type=Local feature aggregation2021.03 | 81.6 | 61.8 | |
| GeM-APTraining set=SfM-120k, Net=ResNet-101, Number of local descriptors=0, Feature Type=Global features2021.03 | 80.1 | 52.5 | |
| HOW-ASMKTraining set=SfM-120k, Net=ResNet-50, Number of local descriptors=1000, Feature Type=Local feature aggregation2021.03 | 80.1 | 58.4 | |
| R-MACTraining set=Landmarks, Net=ResNet-101, Number of local descriptors=0, Feature Type=Global features2021.03 | 78.9 | 54.8 | |
| GeM + DSMTraining set=SfM-120k, Net=ResNet-101, Number of local descriptors=1000, Feature Type=Global features + Re-ranking2021.03 | 77.4 | 52.8 | |
| GeMTraining set=SfM-120k, Net=ResNet-101, Number of local descriptors=0, Feature Type=Global features2021.03 | 77.2 | 52.3 | |
| DELF-ASMKTraining set=Landmarks, Net=ResNet-50, Number of local descriptors=1000, Feature Type=Local feature aggregation2021.03 | 76.9 | 57.3 |