vgg8 (T:vgg13 S:vgg8)

Reported on 1 benchmark across 1 task · 5 papers

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

Natural Language Processing5 results

Knowledge DistillationonCIFAR-100
Top-1 Accuracy (%)· 2021-12-01
74.93
best: 79.86 (SRD (T:resnet-32x4, S:shufflenet-v2))
Information Theoretic Representation Distillation arXiv:2112.00459
Knowledge DistillationonCIFAR-100
Top-1 Accuracy (%)· 2021-04-19
74.84
best: 79.86 (SRD (T:resnet-32x4, S:shufflenet-v2))
Distilling Knowledge via Knowledge Review arXiv:2104.09044
Knowledge DistillationonCIFAR-100
Top-1 Accuracy (%)· 2020-12-15
74.72
best: 79.86 (SRD (T:resnet-32x4, S:shufflenet-v2))
Wasserstein Contrastive Representation Distillation arXiv:2012.08674
Knowledge DistillationonCIFAR-100
Top-1 Accuracy (%)· 2019-10-23
74.29
best: 79.86 (SRD (T:resnet-32x4, S:shufflenet-v2))
Contrastive Representation Distillation arXiv:1910.10699
Knowledge DistillationonCIFAR-100
Top-1 Accuracy (%)· 2015-03-09
72.98
best: 79.86 (SRD (T:resnet-32x4, S:shufflenet-v2))
Distilling the Knowledge in a Neural Network arXiv:1503.02531