Image Classification on CIFAR-100 (test val)
85.4Top-1 AccuracyLR-LoRA
Evaluation results
| Method | Links | |
|---|---|---|
| LR-LoRABackbone=CLIP ViT-B/32, Rank (r)=16, Adapter Placement=attention and MLP projections, Number of Seeds=32026.06 | 85.4 | |
| RandLoRABackbone=CLIP ViT-B/32, Rank (r)=16, Adapter Placement=attention and MLP projections, Number of Seeds=32026.06 | 84.6 | |
| LoRABackbone=CLIP ViT-B/32, Rank (r)=16, Adapter Placement=attention and MLP projections, Number of Seeds=32026.06 | 84.2 | |
| VeRABackbone=CLIP ViT-B/32, Rank (r)=16, Adapter Placement=attention and MLP projections, Number of Seeds=32026.06 | 83.9 |