List your company
ResearchFormerly WizWand

Image Retrieval on Paris106k (test)

93.2mAPR-MAC+QE
56.59266.09675.685.104Nov 18, 2015Mar 16, 2016Jul 13, 2016Nov 10, 2016Mar 9, 2017Jul 6, 2017Nov 3, 2017
Updated 8mo ago

Evaluation results

MethodLinks
R-MAC+QENet=Res, F-tuned=yes, Dim=20482017.1193.2
GeM+alphaQENet=Res, F-tuned=yes, Dim=20482017.1191.9
R-MACNet=Res, F-tuned=yes, Dim=20482017.1190.6
GeM+alphaQENet=VGG, F-tuned=yes, Dim=5122017.1187.6
GeMNet=Res, F-tuned=yes, Dim=20482017.1186.9
R-MAC+QENet=VGG, F-tuned=yes, Dim=5122017.1186.8
R-MAC+QENet=Res, F-tuned=no, Dim=20482017.1185.3
GeMNet=VGG, F-tuned=yes, Dim=5122017.1181.3
R-MAC+AML+QE2015.1179.8
R-MAC+R+QENet=VGG, F-tuned=no, Dim=5122017.1179.8
R-MACNet=VGG, F-tuned=yes, Dim=5122017.1179.7
CroW+QENet=VGG, F-tuned=no, Dim=5122017.1179.4
R-MACNet=Res, F-tuned=no, Dim=20482017.1177.8
Mikulik et al. (2013)2015.1177.3
BoW-fVocab+R+QENet=n/a, F-tuned=n/a, Dim=n/a2017.1177.3
R-MACDimensionality=512, Backbone=VGG, Training Protocol=Fine-tuned, Query Cropping=Crop2016.0476.4
R-MACD=5122015.1175.7
R-MACNet=VGG, F-tuned=no, Dim=5122017.1175.7
CroWNet=VGG, F-tuned=no, Dim=5122017.1172.2
Chum et al. (2011)2015.1171
BoW+R+QENet=n/a, F-tuned=n/a, Dim=n/a2017.1171
SPOCNet=VGG, F-tuned=no, Dim=5122017.1168.4
BoW-CNNNet=VGG, F-tuned=no, Dim=n/a2017.1164.8
BOW-CNN+R+QENet=VGG, F-tuned=no, Dim=n/a2017.1164.1
R-MACD=2562015.1160.1
MACNet=VGG, F-tuned=no, Dim=5122017.1158