AdaBoosting Text Prompts for Vision-Language Models
Open paper
Benchmark
Model
Rank
Results
few-shot-image-classification-on-dtd-16-shot
TPB (16-shot, OpenAI CLIP RN50)
#3
Accuracy: 62.8
few-shot-image-classification-on-eurosat-16-shot
TPB (16-shot, OpenAI CLIP RN50)
#4
Accuracy: 66.9
Rank counts only results with a code link.