List your company
ResearchFormerly WizWand

Teachable Object Recognition on ORBIT CLE-VE 1.0 (test)

82.7Frame AccuracySimple CNAPs + LITE
64.569.22573.9578.675Jul 2, 2021
Updated 8mo ago

Evaluation results

MethodLinks
Simple CNAPs + LITEBackbone=EfficientNet-B0, Image Size=224, LITE Training=true, MACs to adapt=3.39T, Steps to adapt=1F, Wall clock time=2.92s, Number of parameters=5.67M2021.0782.74.191.8
ProtoNets + LITEBackbone=EfficientNet-B0, Image Size=224, LITE Training=true, MACs to adapt=1.21T, Steps to adapt=1F, Wall clock time=1.72s, Number of parameters=4.01M2021.0782.13.991.2
Simple CNAPsBackbone=EfficientNet-B0, Image Size=224, LITE Training=false, MACs to adapt=3.39T, Steps to adapt=1F, Wall clock time=2.91s, Number of parameters=5.67M2021.0781.44.988.3
CNAPsBackbone=EfficientNet-B0, Image Size=224, LITE Training=false, MACs to adapt=3.38T, Steps to adapt=1F, Wall clock time=2.83s, Number of parameters=10.59M2021.0779.66.287
CNAPsBackbone=EfficientNet-B0, Image Size=224, LITE Training=true, MACs to adapt=3.38T, Steps to adapt=1F, Wall clock time=2.85s, Number of parameters=10.59M2021.0779.65.987.6
MAMLBackbone=EfficientNet-B0, Image Size=224, LITE Training=false, MACs to adapt=36.31T, Steps to adapt=15FB, Wall clock time=117.89s, Number of parameters=4.01M2021.0779.36.287.5
ProtoNetsBackbone=EfficientNet-B0, Image Size=224, LITE Training=false, MACs to adapt=1.21T, Steps to adapt=1F, Wall clock time=1.72s, Number of parameters=4.01M2021.0778.44.787.9
FineTunerBackbone=EfficientNet-B0, Image Size=224, LITE Training=false, MACs to adapt=121.02T, Steps to adapt=50FB, Wall clock time=139.99s, Number of parameters=4.01M2021.0778.15.885.9
ProtoNetsBackbone=ResNet-18, Image Size=224, LITE Training=false, MACs to adapt=5.47T, Steps to adapt=1F, Wall clock time=1.07s, Number of parameters=11.18M2021.0777.44.587.1
ProtoNets + LITEBackbone=ResNet-18, Image Size=224, LITE Training=true, MACs to adapt=5.47T, Steps to adapt=1F, Wall clock time=1.07s, Number of parameters=11.18M2021.0776.75.186.4
Simple CNAPs + LITEBackbone=ResNet-18, Image Size=224, LITE Training=true, MACs to adapt=7.64T, Steps to adapt=1F, Wall clock time=2.14s, Number of parameters=11.97M2021.0776.56.186.4
CNAPsBackbone=ResNet-18, Image Size=224, LITE Training=true, MACs to adapt=7.64T, Steps to adapt=1F, Wall clock time=2.11s, Number of parameters=12.76M2021.07765.984.9
MAMLBackbone=ResNet-18, Image Size=224, LITE Training=false, MACs to adapt=163.97T, Steps to adapt=15FB, Wall clock time=65.22s, Number of parameters=11.18M2021.0775.74.986.1
Simple CNAPsBackbone=ResNet-18, Image Size=224, LITE Training=false, MACs to adapt=7.64T, Steps to adapt=1F, Wall clock time=2.13s, Number of parameters=11.97M2021.0775.2684.6
CNAPsBackbone=ResNet-18, Image Size=224, LITE Training=false, MACs to adapt=7.64T, Steps to adapt=1F, Wall clock time=2.11s, Number of parameters=12.76M2021.0773.65.483.4
FineTunerBackbone=ResNet-18, Image Size=224, LITE Training=false, MACs to adapt=546.57T, Steps to adapt=50FB, Wall clock time=96.23s, Number of parameters=11.18M2021.0772.28.781.9
MAMLBackbone=ResNet-18, Image Size=84, LITE Training=false, MACs to adapt=95.31T, Steps to adapt=15FB, Wall clock time=36.98s, Number of parameters=11.17M2021.0770.68.680.9
Simple CNAPsBackbone=ResNet-18, Image Size=84, LITE Training=false, MACs to adapt=3.48T, Steps to adapt=1F, Wall clock time=1.01s, Number of parameters=11.97M2021.0770.37.383
FineTunerBackbone=ResNet-18, Image Size=84, LITE Training=false, MACs to adapt=317.70T, Steps to adapt=50FB, Wall clock time=53.94s, Number of parameters=11.17M2021.0769.57.879.7
CNAPsBackbone=ResNet-18, Image Size=84, LITE Training=false, MACs to adapt=3.48T, Steps to adapt=1F, Wall clock time=0.98s, Number of parameters=12.75M2021.0766.28.479.6
ProtoNetsBackbone=ResNet-18, Image Size=84, LITE Training=false, MACs to adapt=3.18T, Steps to adapt=1F, Wall clock time=0.73s, Number of parameters=11.17M2021.0765.27.681.9