Object Hallucination Evaluation on OPOPE MSCOCO (test)
73.5AccuracyMPD
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| MPDBase Model=LLaVA-1.52026.04 | 73.5 | 96.32 | 93.4 | |
| MPDBase Model=mPLUG-Owl22026.04 | 72.86 | 97.78 | 93.5 | |
| NuliBase Model=LLaVA-1.52026.04 | 72.52 | 94.46 | 92.79 | |
| NuliBase Model=mPLUG-Owl22026.04 | 71.04 | 96.3 | 92.05 | |
| DoLABase Model=LLaVA-1.52026.04 | 70.69 | 90.87 | 87.59 | |
| VCDBase Model=LLaVA-1.52026.04 | 70.67 | 91.62 | 88.19 | |
| HALCBase Model=LLaVA-1.52026.04 | 70.59 | 92.94 | 89.22 | |
| GreedyBase Model=LLaVA-1.52026.04 | 70.56 | 91.08 | 87.72 | |
| DoLABase Model=mPLUG-Owl22026.04 | 70.17 | 91.97 | 88.3 | |
| HALCBase Model=mPLUG-Owl22026.04 | 70.12 | 91.94 | 88.26 | |
| LUREBase Model=LLaVA-1.52026.04 | 70 | 90.89 | 87.38 | |
| VCDBase Model=mPLUG-Owl22026.04 | 69.81 | 92.7 | 88.76 | |
| MPDBase Model=MiniGPT-42026.04 | 69.79 | 97.83 | 92.6 | |
| GreedyBase Model=mPLUG-Owl22026.04 | 69.77 | 91.07 | 87.45 | |
| OPERABase Model=LLaVA-1.52026.04 | 69.73 | 91.1 | 87.46 | |
| OPERABase Model=mPLUG-Owl22026.04 | 69.26 | 93.06 | 88.83 | |
| LUREBase Model=mPLUG-Owl22026.04 | 69.24 | 90.54 | 86.85 | |
| NuliBase Model=MiniGPT-42026.04 | 68.81 | 96.49 | 91.21 | |
| LUREBase Model=MiniGPT-42026.04 | 68.14 | 90.95 | 86.76 | |
| OPERABase Model=MiniGPT-42026.04 | 67.26 | 90.76 | 86.25 | |
| DoLABase Model=MiniGPT-42026.04 | 67.06 | 90.84 | 86.22 | |
| GreedyBase Model=MiniGPT-42026.04 | 66.78 | 90.43 | 85.79 | |
| HALCBase Model=MiniGPT-42026.04 | 66.76 | 91.95 | 86.92 | |
| VCDBase Model=MiniGPT-42026.04 | 65.78 | 90.02 | 85 |