List your company

Object Detection on COCO (AP^b, NID)

58AP^bTC-JEPA
37.40842.75448.153.446Mar 20, 2026Mar 29, 2026Apr 7, 2026Apr 16, 2026Apr 25, 2026May 4, 2026May 14, 2026

Evaluation results

MethodLinks
TC-JEPABackbone=ViT-L/14, Pre-training Data=CC27M2026.0558—
TC-JEPABackbone=ViT-B/16, Pre-training Data=CC27M2026.0555.6—
TC-JEPAViT=H/142026.0555.2—
TC-JEPABackbone=ViT-B/16, Pre-training Data=YFCC15M2026.0554.5—
I-JEPAViT=H/142026.0553.7—
StoPViT=H/142026.0553.5—
data2vecViT=L/162026.0552.9—
SPARCBackbone=ViT-B/16, Pre-training Data=CC27M2026.0552.6—
TC-JEPAViT=B/162026.0552.6—
SPARCBackbone=ViT-B/16, Pre-training Data=YFCC15M2026.0552—
Full-precisionNetwork=Swin-S + Cascade Mask R-CNN, #Bits=32/32, Size=427.82026.0551.9—
Full-precisionNetwork=Swin-B + Cascade Mask R-CNN, #Bits=32/32, Size=579.92026.0551.9—
RepQ-ViT + NBCNetwork=Swin-S + Cascade Mask R-CNN, #Bits=6/6, Size=91.32026.0551.7—
RepQ-ViT + NBCNetwork=Swin-B + Cascade Mask R-CNN, #Bits=6/6, Size=126.12026.0551.7—
RepQ-ViTNetwork=Swin-B + Cascade Mask R-CNN, #Bits=6/6, Size=112.12026.0551.5—
RepQ-ViTNetwork=Swin-S + Cascade Mask R-CNN, #Bits=6/6, Size=83.42026.0551.4—
iBOTViT=B/162026.0551.2—
DreamLIPBackbone=ViT-B/16, Pre-training Data=CC30M2026.0550.7—
MAEViT=H/142026.0550.1—
DINOViT=B/162026.0550.1—
RepQ-ViT + NBCNetwork=Swin-B + Cascade Mask R-CNN, #Bits=4/4, Size=90.12026.0549.6—
RepQ-ViT + NBCNetwork=Swin-S + Cascade Mask R-CNN, #Bits=4/4, Size=64.82026.0549.4—
RepQ-ViTNetwork=Swin-B + Cascade Mask R-CNN, #Bits=4/4, Size=76.12026.0549.3—
RepQ-ViTNetwork=Swin-S + Cascade Mask R-CNN, #Bits=4/4, Size=56.92026.0549.1—
EvoNet-C3Params=42M, MACs=228G, Lat.=66.9ms, Thrp.=18, Test Resolution=800 × 1280, Framework=Mask R-CNN [40]2026.0348.51.15
Full-precisionNetwork=Swin-S + Mask R-CNN, #Bits=32/32, Size=276.52026.0548.5—
RepQ-ViT + NBCNetwork=Swin-S + Mask R-CNN, #Bits=6/6, Size=61.22026.0547.8—
Spatial-Mamba-TParams=46M, MACs=261G, Lat.=51.0ms, Thrp.=20, Test Resolution=800 × 1280, Framework=Mask R-CNN [40]2026.0347.61.03
RepQ-ViTNetwork=Swin-S + Mask R-CNN, #Bits=6/6, Size=53.32026.0547.6—
DreamLIPBackbone=ViT-B/16, Pre-training Data=YFCC15M2026.0547.2—
EvoNet-C2Params=36M, MACs=202G, Lat.=55.4ms, Thrp.=23, Test Resolution=800 × 1280, Framework=Mask R-CNN [40]2026.0347.11.29
LocalVMamba-TParams=45M, MACs=291G, Lat.=108.8ms, Thrp.=8, Test Resolution=800 × 1280, Framework=Mask R-CNN [40]2026.0346.71.04
VMamba-TParams=42M, MACs=262G, Lat.=74.3ms, Thrp.=12, Test Resolution=800 × 1280, Framework=Mask R-CNN [40]2026.0346.51.11
MPViT-SParams=43M, MACs=268G, Test Resolution=800 × 1280, Framework=Mask R-CNN [40]2026.0346.41.08
ViTAS-Twins-SParams=44M, MACs=168G, Test Resolution=800 × 1280, Framework=Mask R-CNN [40]2026.0345.91.04
EvoNet-C1Params=33M, MACs=190G, Lat.=50.2ms, Thrp.=26, Test Resolution=800 × 1280, Framework=Mask R-CNN [40]2026.0345.41.39
MaskCLIPBackbone=ViT-B/16, Pre-training Data=YFCC15M2026.0545.4—
PVTv2-B2Params=45M, Lat.=86.7ms, Thrp.=7, Test Resolution=800 × 1280, Framework=Mask R-CNN [40]2026.0345.31.01
ViT-Adapter-SParams=48M, MACs=403G, Lat.=138.7ms, Thrp.=7, Test Resolution=800 × 1280, Framework=Mask R-CNN [40]2026.0344.70.93
GroupViTBackbone=ViT-S/16, Pre-training Data=CC27M2026.0544.3—
ConvNeXt-TParams=48M, MACs=262G, Lat.=43.4ms, Thrp.=26, Test Resolution=800 × 1280, Framework=Mask R-CNN [40]2026.0344.20.92
CLIPBackbone=ViT-B/16, Pre-training Data=YFCC15M2026.0543.6—
BLIPBackbone=ViT-B/16, Pre-training Data=Merged14M2026.0543.1—
RepQ-ViT + NBCNetwork=Swin-S + Mask R-CNN, #Bits=4/4, Size=44.02026.0543—
RepQ-ViTNetwork=Swin-S + Mask R-CNN, #Bits=4/4, Size=36.12026.0542.8—
Swin-TParams=48M, MACs=267G, Lat.=45.1ms, Thrp.=24, Test Resolution=800 × 1280, Framework=Mask R-CNN [40]2026.0342.70.89
PVT-S+AttnZeroMACs=248G, Lat.=51.3ms, Thrp.=23, Test Resolution=800 × 1280, Framework=Mask R-CNN [40]2026.0341—
UniNet-B1Params=28M, MACs=150G, Lat.=45.7ms, Thrp.=24, Test Resolution=800 × 1280, Framework=Mask R-CNN [40]2026.0340.51.45
ResNet-50Params=44M, MACs=260G, Lat.=32.8ms, Thrp.=34, Test Resolution=800 × 1280, Framework=Mask R-CNN [40]2026.0338.20.87