Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Object Hallucination Detection on POPE averaged across MS-COCO, A-OKVQA, and GQA (Random)
Loading...
90.1
Accuracy
VAF
87.5
88.175
88.85
89.525
Mar 17, 2025
Accuracy
F1 Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
F1 Score
VAF
Backbone=LLaVA-v1.5-13B
2025.03
90.1
89.9
VAF
Backbone=Qwen-VL-Chat-7B
2025.03
90
89.7
VAF
Backbone=LLaVA-v1.5-7B
2025.03
89.6
89.3
VCD
Backbone=Qwen-VL-Chat-7B
2025.03
89.1
88.4
VCD
Backbone=LLaVA-v1.5-13B
2025.03
88.9
87.8
ICD
Backbone=Qwen-VL-Chat-7B
2025.03
88.9
88.1
VCD
Backbone=LLaVA-v1.5-7B
2025.03
88.4
87.7
Regular
Backbone=Qwen-VL-Chat-7B
2025.03
88.2
87.9
ICD
Backbone=LLaVA-v1.5-7B
2025.03
88.1
87.6
ICD
Backbone=LLaVA-v1.5-13B
2025.03
88.1
87.6
Regular
Backbone=LLaVA-v1.5-7B
2025.03
87.8
87.5
Regular
Backbone=LLaVA-v1.5-13B
2025.03
87.6
87.4
Feedback
Search any
task
Search any
task