List your company

Gender Classification on COCO 95% spurious correlation

78.1Average ScoreBAP
54.760.77566.8572.925May 11, 2026

Evaluation results

MethodLinks
BAPBackbone=CLIP, Evaluation Protocol=Linear Probing2026.0578.175.7
Data-Matched ControlBackbone=SigLIP2, Evaluation Protocol=Trained Evaluation2026.0578.176.2
BAPBackbone=SigLIP2, Evaluation Protocol=Linear Probing2026.0577.675.8
BAPBackbone=SigLIP2, Evaluation Protocol=Zero-Shot2026.0577.571.8
Data-Matched ControlBackbone=CLIP, Evaluation Protocol=Trained Evaluation2026.0575.273.8
DFRBackbone=SigLIP2, Evaluation Protocol=Trained Evaluation2026.0575.271.4
DIALBackbone=CLIP, Evaluation Protocol=Zero-Shot2026.0575.153.8
BAPBackbone=CLIP, Evaluation Protocol=Zero-Shot2026.0574.257.1
DFRBackbone=CLIP, Evaluation Protocol=Trained Evaluation2026.0574.266.8
AFRBackbone=CLIP, Evaluation Protocol=Trained Evaluation2026.0573.364.7
RoboShotBackbone=CLIP, Evaluation Protocol=Zero-Shot2026.0573.252.5
RoboShotBackbone=SigLIP2, Evaluation Protocol=Zero-Shot2026.0572.967
DIALBackbone=SigLIP2, Evaluation Protocol=Zero-Shot2026.0572.465.2
Native BackboneBackbone=CLIP, Evaluation Protocol=Zero-Shot2026.0571.448.3
Native BackboneBackbone=SigLIP2, Evaluation Protocol=Zero-Shot2026.0571.364.2
WiSE-FTBackbone=SigLIP2, Evaluation Protocol=Trained Evaluation2026.0565.753.2
ERMBackbone=SigLIP2, Evaluation Protocol=Linear Probing & Fine-Tuning2026.0563.341.2
WiSE-FTBackbone=CLIP, Evaluation Protocol=Trained Evaluation2026.0563.157.4
ERMBackbone=CLIP, Evaluation Protocol=Linear Probing & Fine-Tuning2026.0560.354.2
Native BackboneBackbone=SigLIP2, Evaluation Protocol=Linear Probing2026.0558.932.3
PruSCBackbone=SigLIP2, Evaluation Protocol=Trained Evaluation2026.0557.545.9
Native BackboneBackbone=CLIP, Evaluation Protocol=Linear Probing2026.0557.323.4
AFRBackbone=SigLIP2, Evaluation Protocol=Trained Evaluation2026.0556.868.6
PruSCBackbone=CLIP, Evaluation Protocol=Trained Evaluation2026.0555.648.6