WTTM (T:resnet50, S:mobilenet-v1)

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 %· 2024-02-17
73.09
best: 86.43 (ScaleKD (T:BEiT-L S:ViT-B/14))
Knowledge Distillation Based on Transformed Teacher Matching arXiv:2402.11148