Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Visual Hallucination Evaluation on POPE MS-COCO (Popular Sampling, val)
Loading...
82.77
Accuracy
InstructBLIP-14B
48.554
57.437
66.32
75.203
Sep 20, 2023
Accuracy
Precision
Recall
F1 Score
Yes Rate
Updated 3d ago
Evaluation Results
Method
Method
Links
Accuracy
Precision
Recall
F1 Score
Yes Rate
InstructBLIP-14B
zero-shot=true, backbo...
2023.09
82.77
76.27
95.13
84.66
62.37
DREAMLLM-7B
zero-shot=true, backbo...
2023.09
80.07
75.74
88.47
81.61
58.4
MiniGPT-4-14B
zero-shot=true, backbo...
2023.09
69.73
65.86
81.93
73.02
62.2
mPLUG-Owl-7B
zero-shot=true, backbo...
2023.09
50.9
50.46
99.4
66.94
98.57
MMGPT-7B
zero-shot=true, backbo...
2023.09
50
50
100
66.67
100
LLaVA-13B
zero-shot=true, backbo...
2023.09
49.87
49.93
99.27
66.44
99.4
Feedback
Search any
task
Search any
task