Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Harmful meme detection on Harm-P (test)
Loading...
90.73
Accuracy
EXPLAINHM
72.4364
77.1857
81.935
86.6843
Jan 24, 2024
Accuracy
Macro F1
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Macro F1
EXPLAINHM
2024.01
90.73
90.72
MOMENTA
2024.01
89.84
88.26
Pro-Cap
2024.01
89.32
87.91
MaskPrompt
2024.01
88.17
87.09
VILBERT CC
Pre-training dataset=CC
2024.01
87.25
86.03
VisualBERT COCO
Pre-training dataset=COCO
2024.01
86.8
86.07
MMBT
2024.01
82.54
80.23
Text BERT
2024.01
80.12
78.35
Late Fusion
2024.01
78.26
78.5
Image-Region
2024.01
73.14
72.77
Feedback
Search any
task
Search any
task