FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformer
Open paper
Benchmark
Model
Rank
Results
monocular-depth-estimation-on-clevr-distance
FacT-TT ViT-B/16 (VTAB-1k)
–
Accuracy: 69.0
object-counting-on-clevr-count
FacT-TK ViT-B/16 (VTAB-1k)
–
Accuracy: 82.6
Rank counts only results with a code link.