Towards Efficient Visual Adaption via Structural Re-parameterization
Open paper
Benchmark
Model
Rank
Results
monocular-depth-estimation-on-clevr-distance
RepAdapter-attn ViT-B/16 (VTAB-1k)
–
Accuracy: 69.1
object-counting-on-clevr-count
RepAdapter ViT-B/16 (VTAB-1k)
–
Accuracy: 82.3
Rank counts only results with a code link.