List your company
ResearchFormerly WizWand

Instance Segmentation on COCO (AP Mask, Delta)

46AP MaskMONA
39.03240.84142.6544.459Aug 15, 2024Sep 20, 2024Oct 27, 2024Dec 3, 2024Jan 9, 2025Feb 15, 2025Mar 24, 2025
Updated 8mo ago

Evaluation results

MethodLinks
MONABackbone=Swin-B (89M), Framework=Cascade Mask R-CNN, Trained Params=4.16 M, Trainable backbone parameters %=4.67%, Extra Structure=true2024.08460.9
FULLBackbone=Swin-B (89M), Framework=Cascade Mask R-CNN, Trained Params=89.14 M, Trainable backbone parameters %=100.00%, Extra Structure=false2024.0845.1—
ADAPTERBackbone=Swin-B (89M), Framework=Cascade Mask R-CNN, Trained Params=3.19 M, Trainable backbone parameters %=3.58%, Extra Structure=true2024.0845-0.1
LORANDBackbone=Swin-B (89M), Framework=Cascade Mask R-CNN, Trained Params=4.68 M, Trainable backbone parameters %=5.23%, Extra Structure=true2024.0844.7-0.4
ADAPTFORMERBackbone=Swin-B (89M), Framework=Cascade Mask R-CNN, Trained Params=1.60 M, Trainable backbone parameters %=1.79%, Extra Structure=true2024.0844.6-0.5
LORABackbone=Swin-B (89M), Framework=Cascade Mask R-CNN, Trained Params=3.06 M, Trainable backbone parameters %=3.43%, Extra Structure=true2024.0843.9-1.2
PARTIAL-1Backbone=Swin-B (89M), Framework=Cascade Mask R-CNN, Trained Params=12.95 M, Trainable backbone parameters %=14.53%, Extra Structure=false2024.0843.7-1.4
BITFITBackbone=Swin-B (89M), Framework=Cascade Mask R-CNN, Trained Params=0.21 M, Trainable backbone parameters %=0.23%, Extra Structure=false2024.0843.6-1.5
NORMTUNINGBackbone=Swin-B (89M), Framework=Cascade Mask R-CNN, Trained Params=0.06 M, Trainable backbone parameters %=0.07%, Extra Structure=false2024.0843.5-1.6
FIXEDBackbone=Swin-B (89M), Framework=Cascade Mask R-CNN, Trained Params=0.00 M, Trainable backbone parameters %=0.00%, Extra Structure=false2024.0841.6-3.5
ConvNeXt-T + FDConvBackbone=ConvNeXt-T, Detector=Mask R-CNN, Params=51M, FLOPS=263G, Training Schedule=1x2025.0340.8—
ConvNeXt-T + KWBackbone=ConvNeXt-T, Detector=Mask R-CNN, Params=52M, FLOPS=262G, Training Schedule=1x2025.0340.6—
Swin-T + FDConvBackbone=Swin-T, Detector=Mask R-CNN, Params=51M, FLOPS=268G, Training Schedule=1x2025.0340.5—
ConvNeXt-TBackbone=ConvNeXt-T, Detector=Mask R-CNN, Params=48M, FLOPS=262G, Training Schedule=1x2025.0339.7—
Swin-TBackbone=Swin-T, Detector=Mask R-CNN, Params=48M, FLOPS=267G, Training Schedule=1x2025.0339.3—