ScaleKD (T:Swin-L S:ResNet-50)

Reported on 1 benchmark across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing1 result

Knowledge DistillationonImageNet
Top-1 accuracy %· 2024-11-11
82.55
best: 86.43 (ScaleKD (T:BEiT-L S:ViT-B/14))
ScaleKD: Strong Vision Transformers Could Be Excellent Teachers arXiv:2411.06786