Visual Question Answering on VQA (std)
76.1AccuracyVinVL
Evaluation Results
| Method | Links | |
|---|---|---|
| VinVL#Img=6M, Encoder Type=Object Detector (O.D.)2023.04 | 76.1 | |
| SoftMask++#Img=4M, Encoder Type=Detector-Free (D.F.)2023.04 | 75.1 | |
| TCL#Img=4M, Encoder Type=Detector-Free (D.F.)2023.04 | 74.9 | |
| CODIS#Img=4M, Encoder Type=Detector-Free (D.F.)2023.04 | 74.9 | |
| ALBEF#Img=4M, Encoder Type=Detector-Free (D.F.)2023.04 | 74.7 | |
| UNIMO#Img=4M, Encoder Type=Object Detector (O.D.)2023.04 | 74 | |
| VILLA#Img=4M, Encoder Type=Object Detector (O.D.)2023.04 | 73.7 | |
| OSCAR#Img=4M, Encoder Type=Object Detector (O.D.)2023.04 | 73.4 | |
| UNITER#Img=4M, Encoder Type=Object Detector (O.D.)2023.04 | 72.9 |