|
SRD (T:resnet-32x4, S:shufflenet-v2)
|
Understanding the Role of the Projector in Knowle…
|
79.86
|
2023-03-20
|
|
|
shufflenet-v2(T:resnet-32x4, S:shufflenet-v2)
|
Logit Standardization in Knowledge Distillation
|
78.76
|
2024-03-03
|
|
|
MV-MR (T: CLIP/ViT-B-16 S: resnet50)
|
MV-MR: multi-views and multi-representations for …
|
78.60
|
2023-03-21
|
|
|
resnet8x4
(T: resnet32x4 S: resnet8x4)
|
Logit Standardization in Knowledge Distillation
|
78.28
|
2024-03-03
|
|
|
resnet8x4 (T: resnet32x4 S: resnet8x4 [modified])
|
Knowledge Distillation with the Reused Teacher Cl…
|
78.08
|
2022-03-26
|
|
|
ReviewKD++(T:resnet-32x4, S:shufflenet-v2)
|
Improving Knowledge Distillation via Regularizing…
|
77.93
|
2023-05-26
|
|
|
ReviewKD++(T:resnet-32x4, S:shufflenet-v1)
|
Improving Knowledge Distillation via Regularizing…
|
77.68
|
2023-05-26
|
|
|
resnet8x4 (T: resnet32x4 S: resnet8x4)
|
LumiNet: The Bright Side of Perceptual Knowledge …
|
77.50
|
2023-10-05
|
|
|
resnet8x4 (T: resnet32x4 S: resnet8x4)
|
Information Theoretic Representation Distillation
|
76.68
|
2021-12-01
|
|
|
resnet8x4 (T: resnet32x4 S: resnet8x4)
|
Knowledge Distillation from A Stronger Teacher
|
76.31
|
2022-05-21
|
|
|
DKD++(T:resnet-32x4, S:resnet-8x4)
|
Improving Knowledge Distillation via Regularizing…
|
76.28
|
2023-05-26
|
|
|
resnet8x4 (T: resnet32x4 S: resnet8x4)
|
Wasserstein Contrastive Representation Distillati…
|
76.15
|
2020-12-15
|
|
|
ReviewKD++(T:WRN-40-2, S:WRN-40-1)
|
Improving Knowledge Distillation via Regularizing…
|
75.66
|
2023-05-26
|
|
|
resnet8x4 (T: resnet32x4 S: resnet8x4)
|
Distilling Knowledge via Knowledge Review
|
75.63
|
2021-04-19
|
|
|
resnet8x4 (T: resnet32x4 S: resnet8x4)
|
Contrastive Representation Distillation
|
75.51
|
2019-10-23
|
|
|
vgg8 (T:vgg13 S:vgg8)
|
Information Theoretic Representation Distillation
|
74.93
|
2021-12-01
|
|
|
vgg8 (T:vgg13 S:vgg8)
|
Distilling Knowledge via Knowledge Review
|
74.84
|
2021-04-19
|
|
|
vgg8 (T:vgg13 S:vgg8)
|
Wasserstein Contrastive Representation Distillati…
|
74.72
|
2020-12-15
|
|
|
vgg8 (T:vgg13 S:vgg8)
|
Contrastive Representation Distillation
|
74.29
|
2019-10-23
|
|
|
resnet8x4 (T: resnet32x4 S: resnet8x4)
|
Distilling the Knowledge in a Neural Network
|
73.33
|
2015-03-09
|
|
|
vgg8 (T:vgg13 S:vgg8)
|
Distilling the Knowledge in a Neural Network
|
72.98
|
2015-03-09
|
|
|
KD++(T:resnet56, S:resnet20)
|
Improving Knowledge Distillation via Regularizing…
|
72.53
|
2023-05-26
|
|
|
resnet110 (T:resnet110 S:resnet20)
|
Information Theoretic Representation Distillation
|
71.99
|
2021-12-01
|
|
|
resnet110 (T:resnet110 S:resnet20)
|
Wasserstein Contrastive Representation Distillati…
|
71.88
|
2020-12-15
|
|
|
resnet110 (T:resnet110 S:resnet20)
|
Contrastive Representation Distillation
|
71.56
|
2019-10-23
|
|
|
DKD++(T:resnet50, S:mobilenetv2)
|
Improving Knowledge Distillation via Regularizing…
|
70.82
|
2023-05-26
|
|
|
resnet110 (T:resnet110 S:resnet20)
|
Distilling the Knowledge in a Neural Network
|
70.67
|
2015-03-09
|
|