List your company
ResearchFormerly WizWand

Scene Classification on Places365 (val)

60.14Top-1 AccuracyFOSNet
35.242441.706248.1754.6338Jul 17, 2019Jul 25, 2019Aug 2, 2019Aug 11, 2019Aug 19, 2019Aug 27, 2019Sep 5, 2019
Updated 8mo ago

Evaluation results

MethodLinks
FOSNetFusion level=feature, Fusion method=mixed CCM-CCG, Backbone=SE-ResNeXt-101, Evaluation protocol=10-crop testing2019.0760.14——88.86——
FOSNetFusion level=feature, Fusion method=Concatenate, Backbone=SE-ResNeXt-101, Evaluation protocol=10-crop testing2019.0760.06——88.78——
FOSNetFusion level=feature, Fusion method=CCG, Backbone=SE-ResNeXt-101, Evaluation protocol=10-crop testing2019.0760.03——88.72——
FOSNetFusion level=score, Fusion method=CCG, Backbone=SE-ResNeXt-101, Evaluation protocol=10-crop testing2019.0759.92——88.69——
FOSNetFusion level=feature, Fusion method=Sum, Backbone=SE-ResNeXt-101, Evaluation protocol=10-crop testing2019.0759.82——88.57——
SE-ResNeXt-101 + SCLTraining loss=Scene Coherence Loss (SCL), Backbone=SE-ResNeXt-101, Evaluation protocol=10-crop testing2019.0759.8——88.66——
SE-Resnet-152Evaluation protocol=10-crop testing, Backbone=ResNet-1522019.0759.63——88.99——
SE-ResNeXt-101Implementation source=our implementation, Evaluation protocol=10-crop testing, Backbone=ResNeXt-1012019.0759.1——88.44——
Places2-365-CNNEvaluation protocol=10-crop testing2019.0758.93——88.52——
Multi-Resolution CNNsEvaluation protocol=10-crop testing2019.0758.3——87.3——
SOSF+CFA+GAFEvaluation protocol=10-crop testing2019.0757.27—————
CNN-SMNEvaluation protocol=10-crop testing2019.0757.1—————
CCMEvaluation protocol=10-crop testing2019.0756.82——86.92——
Semantic-Aware Scene Recognition (Ours)Number of Parameters=~ 47 M2019.0956.51——8671.5756.51
DenseNet-161Number of Parameters=~ 29 M2019.0956.12——86.1271.4856.12
ResNet-50Number of Parameters=~ 25 M2019.0955.47——85.3670.455.47
Places365-VGGEvaluation protocol=10-crop testing2019.0755.24—————
VGG-19Number of Parameters=~ 143 M, Reported in=[1]2019.0955.24——84.91——
ResNet-50Number of Parameters=~ 25 M, Reported in=[1]2019.0954.74——85.08——
GoogLeNetNumber of Parameters=~ 7 M, Reported in=[1]2019.0953.63——83.88——
AlexNetNumber of Parameters=~ 62 M, Reported in=[1]2019.0953.17——82.89——
ResNet-18Number of Parameters=~ 12 M2019.0953.05——83.8668.8754.4
AlexNetNumber of Parameters=~ 62 M2019.0947.45——78.3962.3349.15
Adi-RedEvaluation protocol=10-crop testing2019.0741.87—————
Semantic BranchNumber of Parameters=~ 2.6 M2019.0936.2——68.4850.1136.2
B-CNNBackbone=ResNet-50, Prediction=10-crop2019.04—44.2414.27———
GoogleNetBackbone=GoogleNet, Prediction=10-crop2019.04—46.3716.12———
iSQRT-COV + E-PNBackbone=ResNet-50, Prediction=10-crop2019.04—45.3415.13———
iSQRT-COV-NetBackbone=ResNet-50, Prediction=10-crop2019.04—43.6813.73———
Places-365-CNNevaluation_protocol=single-crop2017.09—41.0711.48———
ResNet-152evaluation_protocol=single-crop, implementation=ours2017.09—41.1511.61———
ResNet-152Backbone=ResNet-152, Prediction=10-crop2019.04—45.2614.92———
ResNet-50Backbone=ResNet-50, Prediction=10-crop2019.04—44.8214.71———
SE-ResNet-152evaluation_protocol=single-crop2017.09—40.3711.01———
VGG-VD16Backbone=VGG-VD16, Prediction=10-crop2019.04—44.7615.09———