Papers with Code · CC BY-SA 4.0

ImageNet

아카이브 평가 52건 · 마지막 적재/변경 2026-10-30

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
ScaleKD (T:BEiT-L S:ViT-B/14)	Top-1 accuracy % 86.43 model size 87M CRD training setting ✘	ScaleKD: Strong Vision Transformers Could Be Excellent Teachers 2024-11-11	코드 1
ScaleKD (T:Swin-L S:ViT-B/16)	Top-1 accuracy % 85.53 model size 87M CRD training setting ✘	ScaleKD: Strong Vision Transformers Could Be Excellent Teachers 2024-11-11	코드 1
ScaleKD (T:Swin-L S:ViT-S/16)	Top-1 accuracy % 83.93 model size 22M CRD training setting ✘	ScaleKD: Strong Vision Transformers Could Be Excellent Teachers 2024-11-11	코드 1
ScaleKD (T:Swin-L S:Swin-T)	Top-1 accuracy % 83.8 model size 27M CRD training setting ✘	ScaleKD: Strong Vision Transformers Could Be Excellent Teachers 2024-11-11	코드 1
KD++(T: regnety-16GF S:ViT-B)	Top-1 accuracy % 83.60 model size 87M CRD training setting ✘	Improving Knowledge Distillation via Regularizing Feature Norm and Direction 2023-05-26	코드 1
VkD (T:RegNety 160 S:DeiT-S)	Top-1 accuracy % 82.9 model size 22M CRD training setting ✘	$V_kD:$ Improving Knowledge Distillation using Orthogonal Projections 2024-03-10	코드 1
SpectralKD (T:Swin-S S:Swin-T)	Top-1 accuracy % 82.7 model size 22M CRD training setting ✘	SpectralKD: A Unified Framework for Interpreting and Distilling Vision Transformers via Spectral Analysis 2024-12-26	코드 1
ScaleKD (T:Swin-L S:ResNet-50)	Top-1 accuracy % 82.55 model size 22M CRD training setting ✘	ScaleKD: Strong Vision Transformers Could Be Excellent Teachers 2024-11-11	코드 1
DiffKD (T:Swin-L S: Swin-T)	Top-1 accuracy % 82.5	Knowledge Diffusion for Distillation 2023-05-25	코드 1
DIST (T: Swin-L S: Swin-T)	Top-1 accuracy % 82.3 model size 29M CRD training setting ✘	Knowledge Distillation from A Stronger Teacher 2022-05-21	코드 1 · 코드 2 · 코드 3
SpectralKD (T:Cait-S24 S:DeiT-S)	Top-1 accuracy % 82.2 model size 22M CRD training setting ✘	SpectralKD: A Unified Framework for Interpreting and Distilling Vision Transformers via Spectral Analysis 2024-12-26	코드 1
SRD (T:RegNety 160 S:DeiT-S)	Top-1 accuracy % 82.1 model size 22M CRD training setting ✘	Understanding the Role of the Projector in Knowledge Distillation 2023-03-20	코드 1 · 코드 2 · 코드 3 · 코드 4
OFA (T: ViT-B S: ResNet-50)	Top-1 accuracy % 81.33	One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation 2023-10-30	코드 1
DiffKD (T:Swin-L S: ResNet-50)	Top-1 accuracy % 80.5	Knowledge Diffusion for Distillation 2023-05-25	코드 1
VkD (T:RegNety 160 S:DeiT-Ti)	Top-1 accuracy % 79.2 model size 6M CRD training setting ✘	$V_kD:$ Improving Knowledge Distillation using Orthogonal Projections 2024-03-10	코드 1
KD++(T:resnet-152 S:resnet-101)	Top-1 accuracy % 79.15 model size 44.5M CRD training setting ✘	Improving Knowledge Distillation via Regularizing Feature Norm and Direction 2023-05-26	코드 1
ADLIK-MO-P25(T:SeNet154, ResNet152b S:ResNet-50-prune25%)	Top-1 accuracy % 78.79 model size 56.9M CRD training setting ✘	Ensemble Knowledge Distillation for Learning Improved and Efficient Networks 2019-09-17	코드 1 · 코드 2
ADLIK-MO-P375(T:SeNet154, ResNet152b S:ResNet-50-prune37.5)	Top-1 accuracy % 78.07 model size 40.5M CRD training setting ✘	Ensemble Knowledge Distillation for Learning Improved and Efficient Networks 2019-09-17	코드 1 · 코드 2
KD++(T:resnet-152 S:resnet-50)	Top-1 accuracy % 77.48 CRD training setting ✘	Improving Knowledge Distillation via Regularizing Feature Norm and Direction 2023-05-26	코드 1
SpectralKD (T:Cait-S24 S:DeiT-T)	Top-1 accuracy % 77.4 model size 6M CRD training setting ✘	SpectralKD: A Unified Framework for Interpreting and Distilling Vision Transformers via Spectral Analysis 2024-12-26	코드 1
SRD (T:RegNety 160 S:DeIT-Ti)	Top-1 accuracy % 77.2 model size 6M CRD training setting ✘	Understanding the Role of the Projector in Knowledge Distillation 2023-03-20	코드 1 · 코드 2 · 코드 3 · 코드 4
ADLIK-MO(T: ResNet101 S: ResNet50)	Top-1 accuracy % 77.14 model size 99M CRD training setting ✘	Distilling the Knowledge in a Neural Network 2015-03-09	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 · 코드 11 · 코드 12 · 코드 13 · 코드 14 · 코드 15 · 코드 16 · 코드 17 · 코드 18 · 코드 19 · 코드 20 · 코드 21 · 코드 22 · 코드 23 · 코드 24 · 코드 25 · 코드 26 · 코드 27 · 코드 28 · 코드 29 · 코드 30 · 코드 31 · 코드 32 · 코드 33 · 코드 34 · 코드 35 · 코드 36 · 코드 37 · 코드 38 · 코드 39 · 코드 40 · 코드 41 · 코드 42 · 코드 43 · 코드 44 · 코드 45 · 코드 46 · 코드 47 · 코드 48 · 코드 49 · 코드 50 · 코드 51 · 코드 52 · 코드 53 · 코드 54 · 코드 55 · 코드 56 · 코드 57 · 코드 58 · 코드 59 · 코드 60 · 코드 61 · 코드 62 · 코드 63 · 코드 64
WTTM (T: DeiT III-Small S:DeiT-Tiny)	Top-1 accuracy % 77.03 CRD training setting ✘	Knowledge Distillation Based on Transformed Teacher Matching 2024-02-17	코드 1
ADLIK-MO-P50(T:SeNet154, ResNet152b S:ResNet-50-half)	Top-1 accuracy % 76.376 model size 27M CRD training setting ✘	Ensemble Knowledge Distillation for Learning Improved and Efficient Networks 2019-09-17	코드 1 · 코드 2
KD++(T:resnet152 S:resnet34)	Top-1 accuracy % 75.53 CRD training setting ✘	Improving Knowledge Distillation via Regularizing Feature Norm and Direction 2023-05-26	코드 1
WTTM (T:resnet50, S:mobilenet-v1)	Top-1 accuracy % 73.09	Knowledge Distillation Based on Transformed Teacher Matching 2024-02-17	코드 1
ReviewKD++(T:resnet50, S:mobilenet-v1)	Top-1 accuracy % 72.96	Improving Knowledge Distillation via Regularizing Feature Norm and Direction 2023-05-26	코드 1
KD++(T:resnet-152 S:resnet18)	Top-1 accuracy % 72.54 CRD training setting ✘	Improving Knowledge Distillation via Regularizing Feature Norm and Direction 2023-05-26	코드 1
KD++(T:renset101 S:resnet18)	Top-1 accuracy % 72.54 CRD training setting ✘	Improving Knowledge Distillation via Regularizing Feature Norm and Direction 2023-05-26	코드 1
KD++(T:resnet50 S:resnet18)	Top-1 accuracy % 72.53 CRD training setting ✘	Improving Knowledge Distillation via Regularizing Feature Norm and Direction 2023-05-26	코드 1