List your company
ResearchFormerly WizWand

Image Retrieval on Tokyo 24/7 (test)

92.9mAPCycleGAN CD
74.779.42584.1588.875Aug 23, 2019Apr 28, 2020Jan 3, 2021Sep 9, 2021May 17, 2022Jan 21, 2023Sep 28, 2023
Updated 8mo ago

Evaluation results

MethodLinks
CycleGAN CDBackbone=ResNet-18, Paired day-night training=false2023.0992.9
CycleGAN CDBackbone=ResNet-18, Paired day-night training data=false2023.0992.9
HED^N GAN CDBackbone=ResNet-101, Paired day-night training data=false2023.0992.2
CycleGAN CDBackbone=ResNet-101, Paired day-night training data=false2023.0992
HEDNGAN CDBackbone=ResNet-18, Paired day-night training=false2023.0991.6
HED^N GAN CDBackbone=ResNet-18, Paired day-night training data=false2023.0991.6
RCFNGAN CDBackbone=ResNet-18, Paired day-night training=false2023.0991.5
CycleGAN CDBackbone=VGG-16, Paired day-night training data=false2023.0990.2
HOW N/DBackbone=ResNet-18, Paired day-night training=true2023.0989.2
HOW N/DBackbone=ResNet-18, Paired day-night training data=true2023.0989.2
HED^N GAN CDBackbone=VGG-16, Paired day-night training data=false2023.0988.9
CIConvBackbone=ResNet-101, Paired day-night training data=false2023.0988.3
HOWBackbone=ResNet-18, Paired day-night training=false2023.0987.8
HOWBackbone=ResNet-18, Paired day-night training data=false2023.0987.8
CLAHETraining Dataset=Retrieval-SfM-N/D, Descriptor Dimension=512D2019.0887
CLAHE N/D CBackbone=VGG-16, Paired day-night training data=true2023.0987
Histogram equalizationTraining Dataset=Retrieval-SfM-N/D, Descriptor Dimension=512D2019.0886.8
U-Net normalizationTraining Dataset=Retrieval-SfM-N/D, Fine-tuning Setup=joint, Descriptor Dimension=512D2019.0886.5
U-Net normalizationTraining Dataset=Retrieval-SfM-N/D, Fine-tuning Setup=embedding, Descriptor Dimension=512D2019.0886.4
EdgeMAC+VGGTraining Dataset=Retrieval-SfM, Descriptor Dimension=1024D2019.0885.4
GeMBackbone=ResNet-101, Paired day-night training data=false2023.0985
Gamma correctionTraining Dataset=Retrieval-SfM-N/D, Descriptor Dimension=512D2019.0884.6
CLAHETraining Dataset=Retrieval-SfM, Descriptor Dimension=512D2019.0884.1
CLAHE CBackbone=VGG-16, Paired day-night training data=false2023.0984.1
VGG GeMTraining Dataset=Retrieval-SfM-N/D, Descriptor Dimension=512D2019.0883.5
GeM N/DBackbone=VGG-16, Paired day-night training data=true2023.0983.5
CIConvBackbone=VGG-16, Paired day-night training data=false2023.0983.3
U-Net normalizationTraining Dataset=Retrieval-SfM-N/D, Fine-tuning Setup=normalization, Descriptor Dimension=512D2019.0883.2
U-Net normalizationTraining Dataset=Retrieval-SfM, Fine-tuning Setup=joint, Descriptor Dimension=512D2019.0879.8
ViTGaLBackbone=XCiT-S24, Training Dataset=GLDv2, Result Source=Reproduced code2023.0979.8
VGG GeMTraining Dataset=Retrieval-SfM, Descriptor Dimension=512D2019.0879.4
GeMBackbone=VGG-16, Paired day-night training data=false2023.0979.4
EdgeMACTraining Dataset=Retrieval-SfM, Descriptor Dimension=512D2019.0875.9
DOLGBackbone=ResNet-101, Training Dataset=GLDv2, Result Source=Reproduced code2023.0975.4