Hierarchical Cross-modal Prompt Learning for Vision-Language Models
Open paper
Benchmark
Model
Rank
Results
prompt-engineering-on-imagenet-s
HiCroPL
#11
Top-1 accuracy %: 49.47
prompt-engineering-on-imagenet-a
HiCroPL
#13
Top-1 accuracy %: 50.79
prompt-engineering-on-imagenet-r
HiCroPL
#15
Top-1 accuracy %: 77.15
Rank counts only results with a code link.