ADLIK-MO-P25(T:SeNet154, ResNet152b S:ResNet-50-prune25%)

Reported on 1 benchmark across 1 task · 1 paper · 1 SOTA

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 %· 2019-09-17
78.79
best: 86.43 (ScaleKD (T:BEiT-L S:ViT-B/14))
SOTA
Ensemble Knowledge Distillation for Learning Improved and Efficient Networks arXiv:1909.08097