List your company
ResearchFormerly WizWand

Instance Segmentation on MS COCO 2014 (test)

45.8APmaskFasterViT-4
41.22442.41243.644.788Jun 9, 2023
Updated 8mo ago

Evaluation results

MethodLinks
FasterViT-4Backbone=FasterViT-4, Throughput (im/sec)=117, Schedule=3x, Detection Framework=Cascade Mask R-CNN, Input Resolution=1280 x 8002023.0645.869.149.8
ConvNeXt-BBackbone=ConvNeXt-B, Throughput (im/sec)=101, Schedule=3x, Detection Framework=Cascade Mask R-CNN, Input Resolution=1280 x 8002023.0645.668.949.5
FasterViT-3Backbone=FasterViT-3, Throughput (im/sec)=159, Schedule=3x, Detection Framework=Cascade Mask R-CNN, Input Resolution=1280 x 8002023.0645.468.749.3
FasterViT-2Backbone=FasterViT-2, Throughput (im/sec)=287, Schedule=3x, Detection Framework=Cascade Mask R-CNN, Input Resolution=1280 x 8002023.0645.268.449
Swin-SBackbone=Swin-S, Throughput (im/sec)=119, Schedule=3x, Detection Framework=Cascade Mask R-CNN, Input Resolution=1280 x 8002023.064568.248.8
ConvNeXt-SBackbone=ConvNeXt-S, Throughput (im/sec)=128, Schedule=3x, Detection Framework=Cascade Mask R-CNN, Input Resolution=1280 x 8002023.064568.449.1
Swin-BBackbone=Swin-B, Throughput (im/sec)=90, Schedule=3x, Detection Framework=Cascade Mask R-CNN, Input Resolution=1280 x 8002023.064568.148.9
Swin-TBackbone=Swin-T, Throughput (im/sec)=161, Schedule=3x, Detection Framework=Cascade Mask R-CNN, Input Resolution=1280 x 8002023.0643.766.647.3
ConvNeXt-TBackbone=ConvNeXt-T, Throughput (im/sec)=166, Schedule=3x, Detection Framework=Cascade Mask R-CNN, Input Resolution=1280 x 8002023.0643.766.547.3
X101-64Backbone=X101-64, Throughput (im/sec)=86, Schedule=3x, Detection Framework=Cascade Mask R-CNN, Input Resolution=1280 x 8002023.0641.76445.1
X101-32Backbone=X101-32, Throughput (im/sec)=124, Schedule=3x, Detection Framework=Cascade Mask R-CNN, Input Resolution=1280 x 8002023.0641.663.945.2
DeiT-Small/16Backbone=DeiT-Small/16, Throughput (im/sec)=269, Schedule=3x, Detection Framework=Cascade Mask R-CNN, Input Resolution=1280 x 8002023.0641.464.244.3