Visual Question Answering Suite (VQA-v2, GQA, VizWiz, TextVQA, POPE, TallyQA)
66.42VQA-v2 AccuracyVMamba-S
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| VMamba-SPretrained Dataset=IN1K → ADE20K, Encoder Size=50M, Image Size=512x512, Vision Token #=10242026.03 | 66.42 | 55.68 | 47.44 | 44.42 | 11.86 | 84.01 | 53.91 | 63.21 | |
| VMamba-BPretrained Dataset=IN1K → ADE20K, Encoder Size=89M, Image Size=512x512, Vision Token #=10242026.03 | 66.12 | 55.89 | 40.19 | 44.5 | 12.33 | 84.39 | 53.61 | 62.87 | |
| ViTDet-BPretrained Dataset=IN1K → COCO, Encoder Size=111M, Image Size=1024x1024, Vision Token #=40962026.03 | 65.83 | 53.61 | 50.58 | 43.75 | 11.6 | 84.46 | 55.96 | 63 | |
| VMamba-TPretrained Dataset=IN1K → ADE20K, Encoder Size=30M, Image Size=512x512, Vision Token #=10242026.03 | 65.45 | 55.26 | 40.91 | 44.18 | 11.85 | 83.65 | 55.66 | 62.6 | |
| VMamba-SPretrained Dataset=IN1K → COCO, Encoder Size=50M, Image Size=1333x800, Vision Token #=41502026.03 | 64.87 | 53.98 | 47.73 | 44.24 | 11.93 | 86.47 | 59.21 | 62.78 | |
| ViTDet-HPretrained Dataset=IN1K → COCO, Encoder Size=662M, Image Size=1024x1024, Vision Token #=40962026.03 | 64.43 | 52.62 | 48.99 | 43.93 | 11.5 | 84.29 | 55.95 | 61.89 | |
| DeiT-BPretrained Dataset=IN1K → ADE20K, Encoder Size=134M, Image Size=512x512, Vision Token #=2562026.03 | 63.37 | 53.32 | 49.4 | 43.98 | 11.97 | 81.64 | 53.11 | 60.69 | |
| DeiT-SPretrained Dataset=IN1K → ADE20K, Encoder Size=58M, Image Size=512x512, Vision Token #=2562026.03 | 61.56 | 52.37 | 52.16 | 44.25 | 11.74 | 79.82 | 53.6 | 59.36 | |
| VMamba-BPretrained Dataset=IN1K → COCO, Encoder Size=89M, Image Size=1333x800, Vision Token #=41502026.03 | 60.36 | 49.21 | 46.46 | 43.84 | 11.73 | 81.61 | 55.69 | 58.57 | |
| VMamba-TPretrained Dataset=IN1K → COCO, Encoder Size=30M, Image Size=1333x800, Vision Token #=41502026.03 | 60.24 | 49.18 | 49.04 | 44.06 | 11.81 | 79.48 | 52.65 | 58.05 | |
| ViTDet-LPretrained Dataset=IN1K → COCO, Encoder Size=331M, Image Size=1024x1024, Vision Token #=40962026.03 | 60 | 48.59 | 44.78 | 43.88 | 11.78 | 78.14 | 51.94 | 57.64 |