SOTAVerified

Knowledge Distillation

Knowledge distillation is the process of transferring knowledge from a large model to a smaller one. While large models (such as very deep neural networks or ensembles of many models) have higher knowledge capacity than small models, this capacity might not be fully utilized.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 801–825 of 4240 papers

TitleStatusHype
Cross-category Video Highlight Detection via Set-based LearningCode1
Baby Llama: knowledge distillation from an ensemble of teachers trained on a small dataset with no performance penaltyCode1
CaKDP: Category-aware Knowledge Distillation and Pruning Framework for Lightweight 3D Object DetectionCode1
Neural Networks Are More Productive Teachers Than Human Raters: Active Mixup for Data-Efficient Knowledge Distillation from a Blackbox ModelCode1
Distilling Autoregressive Models to Obtain High-Performance Non-Autoregressive Solvers for Vehicle Routing Problems with Faster Inference SpeedCode1
Distilling Cross-Task Knowledge via Relationship MatchingCode1
CrossKD: Cross-Head Knowledge Distillation for Object DetectionCode1
Cross-Layer Distillation with Semantic CalibrationCode1
Distilling Holistic Knowledge with Graph Neural NetworksCode1
NORM: Knowledge Distillation via N-to-One Representation MatchingCode1
Distilled Split Deep Neural Networks for Edge-Assisted Real-Time SystemsCode1
Distilled Semantics for Comprehensive Scene Understanding from VideosCode1
One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge DistillationCode1
One-shot Federated Learning via Synthetic Distiller-Distillate CommunicationCode1
Distilling a Powerful Student Model via Online Knowledge DistillationCode1
CrossMatch: Enhance Semi-Supervised Medical Image Segmentation with Perturbation Strategies and Knowledge DistillationCode1
Balanced Knowledge Distillation for Long-tailed LearningCode1
Cross-Modal Fusion Distillation for Fine-Grained Sketch-Based Image RetrievalCode1
Cross-modality Data Augmentation for End-to-End Sign Language TranslationCode1
Online Knowledge Distillation for Efficient Pose EstimationCode1
Cross-Modality Knowledge Distillation Network for Monocular 3D Object DetectionCode1
Online Knowledge Distillation via Mutual Contrastive Learning for Visual RecognitionCode1
Fcaformer: Forward Cross Attention in Hybrid Vision TransformerCode1
DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge DistillationCode1
Distilling Audio-Visual Knowledge by Compositional Contrastive LearningCode1
Show:102550
← PrevPage 33 of 170Next →
All datasetsImageNetCIFAR-100COCO (Common Objects in Context)COCO 2017 valPASCAL VOCKITTI

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ScaleKD (T:BEiT-L S:ViT-B/14)Top-1 accuracy %86.43—Unverified
2ScaleKD (T:Swin-L S:ViT-B/16)Top-1 accuracy %85.53—Unverified
3ScaleKD (T:Swin-L S:ViT-S/16)Top-1 accuracy %83.93—Unverified
4ScaleKD (T:Swin-L S:Swin-T)Top-1 accuracy %83.8—Unverified
5KD++(T: regnety-16GF S:ViT-B)Top-1 accuracy %83.6—Unverified
6VkD (T:RegNety 160 S:DeiT-S)Top-1 accuracy %82.9—Unverified
7SpectralKD (T:Swin-S S:Swin-T)Top-1 accuracy %82.7—Unverified
8ScaleKD (T:Swin-L S:ResNet-50)Top-1 accuracy %82.55—Unverified
9DiffKD (T:Swin-L S: Swin-T)Top-1 accuracy %82.5—Unverified
10DIST (T: Swin-L S: Swin-T)Top-1 accuracy %82.3—Unverified
#ModelMetricClaimedVerifiedStatus
1SRD (T:resnet-32x4, S:shufflenet-v2)Top-1 Accuracy (%)79.86—Unverified
2shufflenet-v2(T:resnet-32x4, S:shufflenet-v2)Top-1 Accuracy (%)78.76—Unverified
3MV-MR (T: CLIP/ViT-B-16 S: resnet50)Top-1 Accuracy (%)78.6—Unverified
4resnet8x4 (T: resnet32x4 S: resnet8x4)Top-1 Accuracy (%)78.28—Unverified
5resnet8x4 (T: resnet32x4 S: resnet8x4 [modified])Top-1 Accuracy (%)78.08—Unverified
6ReviewKD++(T:resnet-32x4, S:shufflenet-v2)Top-1 Accuracy (%)77.93—Unverified
7ReviewKD++(T:resnet-32x4, S:shufflenet-v1)Top-1 Accuracy (%)77.68—Unverified
8resnet8x4 (T: resnet32x4 S: resnet8x4)Top-1 Accuracy (%)77.5—Unverified
9resnet8x4 (T: resnet32x4 S: resnet8x4)Top-1 Accuracy (%)76.68—Unverified
10resnet8x4 (T: resnet32x4 S: resnet8x4)Top-1 Accuracy (%)76.31—Unverified
#ModelMetricClaimedVerifiedStatus
1LSHFM (T: ResNet101 S: ResNet50)mAP77.16—Unverified
2LSHFM (T: ResNet101 S: MobileNetV2)mAP73.73—Unverified
3ADLIK-Faster (T: Faster R-CNN vit-base S: Faster R-CNN deit-small) box AP47.6—Unverified
4ADLIK-Mask (T: Mask R-CNN vit-base S: Mask R-CNN deit-small)mask AP42.4—Unverified
#ModelMetricClaimedVerifiedStatus
1ReviewKD++(T: faster rcnn(resnet101), S:faster rcnn(resnet50))AP@0.561.8—Unverified
2ReviewKD++(T: faster rcnn(resnet101), S:faster rcnn(resnet18))AP@0.557.96—Unverified
3ReviewKD++(T: faster rcnn(resnet101), S:faster rcnn(mobilenet-v2))AP@0.555.18—Unverified
#ModelMetricClaimedVerifiedStatus
1LSHFM (T: ResNet101 S: ResNet50)mAP93.17—Unverified
2LSHFM (T: ResNet101 S: MobileNetV2)mAP90.14—Unverified
#ModelMetricClaimedVerifiedStatus
1TIE-KD (T: Adabins S: MobileNetV2)RMSE2.43—Unverified