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 1351–1400 of 4240 papers

TitleStatusHype
Inter-Domain Alignment for Predicting High-Resolution Brain Networks Using Teacher-Student LearningCode0
Dynamic Rectification Knowledge DistillationCode0
Interpretable Embedding Procedure Knowledge Transfer via Stacked Principal Component Analysis and Graph Neural NetworkCode0
Induced Model Matching: How Restricted Models Can Help Larger OnesCode0
InDistill: Information flow-preserving knowledge distillation for model compressionCode0
Induced Model Matching: Restricted Models Help Train Full-Featured ModelsCode0
Asymmetric Masked Distillation for Pre-Training Small Foundation ModelsCode0
Learning to "Segment Anything" in Thermal Infrared Images through Knowledge Distillation with a Large Scale Dataset SATIRCode0
Closest Neighbors are Harmful for Lightweight Masked Auto-encodersCode0
3M-Health: Multimodal Multi-Teacher Knowledge Distillation for Mental Health DetectionCode0
Complex Facial Expression Recognition Using Deep Knowledge Distillation of Basic FeaturesCode0
DVFL-Net: A Lightweight Distilled Video Focal Modulation Network for Spatio-Temporal Action RecognitionCode0
Leveraging Diffusion-Based Image Variations for Robust Training on Poisoned DataCode0
Leveraging Foundation Models via Knowledge Distillation in Multi-Object Tracking: Distilling DINOv2 Features to FairMOTCode0
Distilling Knowledge by Mimicking FeaturesCode0
Leveraging knowledge distillation for partial multi-task learning from multiple remote sensing datasetsCode0
Incorporating Graph Information in Transformer-based AMR ParsingCode0
Improving Stance Detection with Multi-Dataset Learning and Knowledge DistillationCode0
UNIKD: UNcertainty-filtered Incremental Knowledge Distillation for Neural Implicit RepresentationCode0
Improving Question Answering Performance Using Knowledge Distillation and Active LearningCode0
Improving Respiratory Sound Classification with Architecture-Agnostic Knowledge Distillation from EnsemblesCode0
A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target TrainingCode0
Adversarial Moment-Matching Distillation of Large Language ModelsCode0
Incremental Meta-Learning via Episodic Replay Distillation for Few-Shot Image RecognitionCode0
Infusing Sequential Information into Conditional Masked Translation Model with Self-Review MechanismCode0
Improving Neural Architecture Search Image Classifiers via Ensemble LearningCode0
CLIMB-3D: Continual Learning for Imbalanced 3D Instance SegmentationCode0
Improving generalizability of distilled self-supervised speech processing models under distorted settingsCode0
Improving Knowledge Distillation via Transferring Learning AbilityCode0
Improving Robustness by Enhancing Weak SubnetsCode0
Improving Adversarial Robust Fairness via Anti-Bias Soft Label DistillationCode0
Dual Correction Strategy for Ranking Distillation in Top-N Recommender SystemCode0
Improving End-to-End Speech Translation by Imitation-Based Knowledge Distillation with Synthetic TranscriptsCode0
Improved Knowledge Distillation via Teacher AssistantCode0
Improved Knowledge Distillation for Crowd Counting on IoT DeviceCode0
IE-GAN: An Improved Evolutionary Generative Adversarial Network Using a New Fitness Function and a Generic Crossover OperatorCode0
Improving Neural Topic Models with Wasserstein Knowledge DistillationCode0
Locally Differentially Private Distributed Deep Learning via Knowledge DistillationCode0
KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge DistillationCode0
DSMix: Distortion-Induced Sensitivity Map Based Pre-training for No-Reference Image Quality AssessmentCode0
DSG-KD: Knowledge Distillation from Domain-Specific to General Language ModelsCode0
DS_FusionNet: Dynamic Dual-Stream Fusion with Bidirectional Knowledge Distillation for Plant Disease RecognitionCode0
Hybrid Attention Model Using Feature Decomposition and Knowledge Distillation for Glucose ForecastingCode0
DROP: Poison Dilution via Knowledge Distillation for Federated LearningCode0
AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture SearchCode0
Hybrid Data-Free Knowledge DistillationCode0
Human Guided Exploitation of Interpretable Attention Patterns in Summarization and Topic SegmentationCode0
Enhancing New-item Fairness in Dynamic Recommender SystemsCode0
HVDistill: Transferring Knowledge from Images to Point Clouds via Unsupervised Hybrid-View DistillationCode0
Do You Remember . . . the Future? Weak-to-Strong generalization in 3D Object DetectionCode0
Show:102550
← PrevPage 28 of 85Next →
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