List your company
ResearchFormerly WizWand

Semantic Segmentation on PartNet (test)

53.8mIoUPosPool*
40.07243.63647.250.764Jul 2, 2020
Updated 8mo ago

Evaluation results

MethodLinks
PosPool*param=18.5M, FLOP=6.8G2020.0753.8
adapt weightsparam=18.5M, FLOP=7.2G2020.0753.5
PosPoolparam=18.5M, FLOP=6.8G2020.0753.4
pseudo gridparam=18.5M, FLOP=8.5G2020.0753
point-wise MLPparam=25.6M, FLOP=9.1G2020.0751.5
baseline† (MAX)param=18.5M, FLOP=6.7G, Pooling strategy=MAX, Equation=72020.0747.4
PosPool (S)param=1.1M, FLOP=0.5G, Model Scale=Small2020.0747.2
PosPool* (S)param=1.1M, FLOP=0.5G, Model Scale=Small2020.0747.2
point-wise MLP (S)param=1.6M, FLOP=0.7G, Model Scale=Small2020.0747
PointCNNparam=4.4M, FLOP=23.1G2020.0746.4
adapt weights (S)param=1.2M, FLOP=0.5G, Model Scale=Small2020.0746.1
baseline† (AVG)param=18.5M, FLOP=6.7G, Pooling strategy=AVG, Equation=72020.0745.8
pseudo grid (S)param=1.2M, FLOP=0.9G, Model Scale=Small2020.0745.2
baseline*param=18.5M, FLOP=6.7G, Equation=62020.0744.6
baseline† (MAX, S)param=1.1M, FLOP=0.4G, Pooling strategy=MAX, Model Scale=Small, Equation=72020.0741.2
baseline† (AVG, S)param=1.1M, FLOP=0.4G, Pooling strategy=AVG, Model Scale=Small, Equation=72020.0740.6