List your company
ResearchFormerly WizWand

Classification on Camelyon VTAB 1k (test)

88.1AccuracyLoRA_mul+VPT_add + PACE
72.576.5580.684.65Sep 25, 2024
Updated 8mo ago

Evaluation results

MethodLinks
LoRA_mul+VPT_add + PACEPre-training Method=DINO, Backbone=ViT-B/16, Pre-trained on=ImageNet-1K2024.0988.1
LoRA_mul+VPT_add + PACEPre-training Method=MAE, Backbone=ViT-B/16, Pre-trained on=ImageNet-1K2024.0985.8
LoRA_mul+VPT_addPre-training Method=DINO, Backbone=ViT-B/16, Pre-trained on=ImageNet-1K2024.0985.4
LoRA_mul+VPT_addPre-training Method=MAE, Backbone=ViT-B/16, Pre-trained on=ImageNet-1K2024.0982.7
LinearPre-training Method=DINO, Backbone=ViT-B/16, Pre-trained on=ImageNet-1K2024.0982.5
LinearPre-training Method=MAE, Backbone=ViT-B/16, Pre-trained on=ImageNet-1K2024.0979.9
FullPre-training Method=MAE, Backbone=ViT-B/16, Pre-trained on=ImageNet-1K2024.0974.6
FullPre-training Method=DINO, Backbone=ViT-B/16, Pre-trained on=ImageNet-1K2024.0973.1