Image Retrieval on Paris 6k classic (base)
95.1mAPCiDeR-FT
Evaluation Results
| Method | Links | |
|---|---|---|
| CiDeR-FTTrain Set=SfM-120k, Backbone=ResNet-101, Pooling=GeM, Loss=ArcFace, Fine-tuned=true, Dimension=20482024.04 | 95.1 | |
| DIR+RPNTrain Set=NC-clean, Backbone=ResNet-101, Pooling=RMAC, Loss=Triplet, Fine-tuned=true, End-to-End=true, Dimension=20482024.04 | 94 | |
| Radenovic et al.Train Set=SfM-120k, Backbone=ResNet-101, Pooling=GeM, Loss=Siamese, Fine-tuned=true, Dimension=20482024.04 | 92.7 | |
| CiDeRTrain Set=SfM-120k, Backbone=ResNet-101, Pooling=GeM, Loss=ArcFace, Fine-tuned=false, Dimension=20482024.04 | 92 | |
| GLAMTrain Set=SfM-120k, Backbone=ResNet-101, Pooling=GeM, Loss=ArcFace, Fine-tuned=true, Dimension=5122024.04 | 91.1 | |
| Liao et al.Train Set=Oxford, Paris, Backbone=AlexNet, VGG16, Pooling=CroW, Loss=Softmax, Local, Fine-tuned=true, Dimension=7682024.04 | 90.3 | |
| DIRTrain Set=SfM-120k, Backbone=ResNet-101, Pooling=RMAC, Loss=Triplet, Fine-tuned=true, Dimension=20482024.04 | 86.3 | |
| SOLARTrain Set=SfM-120k, Backbone=ResNet-101, Pooling=GeM, Loss=Triplet, SOS, Fine-tuned=true, Dimension=20482024.04 | 86.3 | |
| DOLGTrain Set=SfM-120k, Backbone=ResNet-101, Pooling=GeM,GAP, Loss=ArcFace, Fine-tuned=true, Dimension=5122024.04 | 74.5 | |
| Salvador et al.Train Set=Pascal VOC, Backbone=VGG16, Pooling=Global Sum Pooling, Loss=Softmax, Local, Fine-tuned=true, Dimension=5122024.04 | 72.9 | |
| Chen et al.Train Set=OpenImageV4, Backbone=ResNet-50, Pooling=MAC, Loss=Softmax, Local, Fine-tuned=true, Dimension=20482024.04 | 65.2 |