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 2551–2600 of 4240 papers

TitleStatusHype
Do Not Blindly Imitate the Teacher: Using Perturbed Loss for Knowledge Distillation—0
Web Content Filtering through knowledge distillation of Large Language Models—0
NeuroComparatives: Neuro-Symbolic Distillation of Comparative Knowledge—0
Structural and Statistical Texture Knowledge Distillation for Semantic Segmentation—0
Distilled Mid-Fusion Transformer Networks for Multi-Modal Human Activity Recognition—0
Smaller3d: Smaller Models for 3D Semantic Segmentation Using Minkowski Engine and Knowledge Distillation MethodsCode0
A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target TrainingCode0
Structure Aware Incremental Learning with Personalized Imitation Weights for Recommender Systems—0
Distill or Annotate? Cost-Efficient Fine-Tuning of Compact Models—0
Detect, Distill and Update: Detect, Distill and Update: Learned DB Systems Facing Out of Distribution DataCode0
Scaffolding a Student to Instill KnowledgeCode0
Refined Response Distillation for Class-Incremental Player DetectionCode0
Ensemble Modeling with Contrastive Knowledge Distillation for Sequential RecommendationCode0
Multi-to-Single Knowledge Distillation for Point Cloud Semantic SegmentationCode0
CORSD: Class-Oriented Relational Self Distillation—0
Learning Human-Human Interactions in Images from Weak Textual Supervision—0
Shape-Net: Room Layout Estimation from Panoramic Images Robust to Occlusion using Knowledge Distillation with 3D Shapes as Additional Inputs—0
A Forward and Backward Compatible Framework for Few-shot Class-incremental Pill RecognitionCode0
Interruption-Aware Cooperative Perception for V2X Communication-Aided Autonomous Driving—0
Improving Knowledge Distillation via Transferring Learning AbilityCode0
Decouple Non-parametric Knowledge Distillation For End-to-end Speech Translation—0
Word Sense Induction with Knowledge Distillation from BERT—0
Biologically inspired structure learning with reverse knowledge distillation for spiking neural networks—0
Knowledge Distillation Under Ideal Joint Classifier Assumption—0
An Empirical Study of Leveraging Knowledge Distillation for Compressing Multilingual Neural Machine Translation Models—0
Deep Collective Knowledge Distillation—0
Learning to "Segment Anything" in Thermal Infrared Images through Knowledge Distillation with a Large Scale Dataset SATIRCode0
LaSNN: Layer-wise ANN-to-SNN Distillation for Effective and Efficient Training in Deep Spiking Neural Networks—0
Always Strengthen Your Strengths: A Drift-Aware Incremental Learning Framework for CTR Prediction—0
Teacher Network Calibration Improves Cross-Quality Knowledge DistillationCode0
Learn What Is Possible, Then Choose What Is Best: Disentangling One-To-Many Relations in Language Through Text-based GamesCode0
Class-Incremental Learning of Plant and Disease Detection: Growing Branches with Knowledge Distillation—0
Constructing Deep Spiking Neural Networks from Artificial Neural Networks with Knowledge Distillation—0
SFT-KD-Recon: Learning a Student-friendly Teacher for Knowledge Distillation in Magnetic Resonance Image ReconstructionCode0
Grouped Knowledge Distillation for Deep Face Recognition—0
A Survey on Recent Teacher-student Learning Studies—0
HyperINR: A Fast and Predictive Hypernetwork for Implicit Neural Representations via Knowledge Distillation—0
Homogenizing Non-IID datasets via In-Distribution Knowledge Distillation for Decentralized Learning—0
A Comprehensive Survey on Knowledge Distillation of Diffusion Models—0
Model-Agnostic Decentralized Collaborative Learning for On-Device POI Recommendation—0
Masked Student Dataset of ExpressionsCode0
Continual Detection Transformer for Incremental Object Detection—0
Self-Distillation for Gaussian Process Regression and ClassificationCode0
Towards Efficient Task-Driven Model Reprogramming with Foundation Models—0
MadEye: Boosting Live Video Analytics Accuracy with Adaptive Camera Configurations—0
Cross-Class Feature Augmentation for Class Incremental Learning—0
Domain Generalization for Crop Segmentation with Standardized Ensemble Knowledge DistillationCode0
Knowledge-Distilled Graph Neural Networks for Personalized Epileptic Seizure Detection—0
A Unified Compression Framework for Efficient Speech-Driven Talking-Face Generation—0
Quick Dense Retrievers Consume KALE: Post Training Kullback Leibler Alignment of Embeddings for Asymmetrical dual encoders—0
Show:102550
← PrevPage 52 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