List your company

Visual Question Answering Suite (VQA-v2, GQA, VizWiz, TextVQA, POPE, TallyQA)

66.42VQA-v2 AccuracyVMamba-S
59.743261.476663.2164.9434Mar 19, 2026

Evaluation results

MethodLinks
VMamba-SPretrained Dataset=IN1K → ADE20K, Encoder Size=50M, Image Size=512x512, Vision Token #=10242026.0366.4255.6847.4444.4211.8684.0153.9163.21
VMamba-BPretrained Dataset=IN1K → ADE20K, Encoder Size=89M, Image Size=512x512, Vision Token #=10242026.0366.1255.8940.1944.512.3384.3953.6162.87
ViTDet-BPretrained Dataset=IN1K → COCO, Encoder Size=111M, Image Size=1024x1024, Vision Token #=40962026.0365.8353.6150.5843.7511.684.4655.9663
VMamba-TPretrained Dataset=IN1K → ADE20K, Encoder Size=30M, Image Size=512x512, Vision Token #=10242026.0365.4555.2640.9144.1811.8583.6555.6662.6
VMamba-SPretrained Dataset=IN1K → COCO, Encoder Size=50M, Image Size=1333x800, Vision Token #=41502026.0364.8753.9847.7344.2411.9386.4759.2162.78
ViTDet-HPretrained Dataset=IN1K → COCO, Encoder Size=662M, Image Size=1024x1024, Vision Token #=40962026.0364.4352.6248.9943.9311.584.2955.9561.89
DeiT-BPretrained Dataset=IN1K → ADE20K, Encoder Size=134M, Image Size=512x512, Vision Token #=2562026.0363.3753.3249.443.9811.9781.6453.1160.69
DeiT-SPretrained Dataset=IN1K → ADE20K, Encoder Size=58M, Image Size=512x512, Vision Token #=2562026.0361.5652.3752.1644.2511.7479.8253.659.36
VMamba-BPretrained Dataset=IN1K → COCO, Encoder Size=89M, Image Size=1333x800, Vision Token #=41502026.0360.3649.2146.4643.8411.7381.6155.6958.57
VMamba-TPretrained Dataset=IN1K → COCO, Encoder Size=30M, Image Size=1333x800, Vision Token #=41502026.0360.2449.1849.0444.0611.8179.4852.6558.05
ViTDet-LPretrained Dataset=IN1K → COCO, Encoder Size=331M, Image Size=1024x1024, Vision Token #=40962026.036048.5944.7843.8811.7878.1451.9457.64