HyperAI

Human Judgment Correlation On Flickr8K Cf

Metrics

Kendall's Tau-b

Results

Performance results of various models on this benchmark

Comparison Table
Model NameKendall's Tau-b
clipscore-a-reference-free-evaluation-metric34.4
mutual-information-divergence-a-unified37.3
clipscore-a-reference-free-evaluation-metric36.4