KD++(T:resnet56, S:resnet20)

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 DistillationonCIFAR-100
Top-1 Accuracy (%)· 2023-05-26
72.53
best: 79.86 (SRD (T:resnet-32x4, S:shufflenet-v2))
Improving Knowledge Distillation via Regularizing Feature Norm and Direction arXiv:2305.17007