ZhangYuanhan-AI / NOAH

Searching prompt modules for parameter-efficient transfer learning.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Few-shot results

Arnav0400 opened this issue · comments

Hi Authors, Great work!

I wanted to know the exact numbers in Figure 4. so as to check the reproducibility and compare with my research. It would be great if you provide the same. Looking forward to hearing from you.

-- Food101 StanfordCars Flowers102 FGVCAircraft OxfordPets
NOAH 31.8 7.3 88.1 8.2 69.7
  51.6 13.2 96.9 13.5 78.1
  63.8 25.5 98.1 23.1 84.9
  71.5 46.2 99.4 34.0 88.0
  76.3 68.6 99.5 49.1 89.0
VPT 23.5 5.5 58.8 6.4 56.8
  46.7 9.6 95.4 11.2 66.1
  60.6 20.7 98.0 19.0 85.3
  67.8 33.5 99.2 28.9 88.6
  72.6 56.0 99.4 42.5 89.6
Lora 31.8 6.7 88.5 9.0 68.6
  48.7 13.5 96.4 13.5 76.1
  59.0 26.4 98.1 22.1 85.7
  66.4 45.9 99.1 34.6 87.3
  72.5 68.2 99.6 47.6 88.7
Adapter 31.4 7.5 88.6 9.1 68.0
  49.0 13.4 96.3 13.3 76.3
  59.8 23.7 98.1 21.1 85.8
  66.8 39.9 99.2 32.0 88.2
  71.7 60.4 99.5 45.2 89.1