Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
VTAB-1k
anchor
Findings
IC-1155
ViT-B/16 (ImageNet-21k) fine-tuned with VPT outperforms full fine-tuning on 16 of 19 VTAB-1k tasks, with the advantage concentrated in high-task-disparity and similar-distribution scenarios and narrowing as downstream data grows
[eval]
IC-1156
The VPT advantage over FT for ViT-B/16 is not explained by overfitting resistance or additional optimization dimensions; the specific feature-preservation mechanism of VPT is the key factor
[eval]