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 2001–2050 of 4240 papers

TitleStatusHype
An Empirical Study of Leveraging Knowledge Distillation for Compressing Multilingual Neural Machine Translation Models—0
Biologically inspired structure learning with reverse knowledge distillation for spiking neural networks—0
Deep Collective Knowledge Distillation—0
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
OVTrack: Open-Vocabulary Multiple Object TrackingCode1
Learning to "Segment Anything" in Thermal Infrared Images through Knowledge Distillation with a Large Scale Dataset SATIRCode0
Robust Cross-Modal Knowledge Distillation for Unconstrained VideosCode1
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
Multi-Mode Online Knowledge Distillation for Self-Supervised Visual Representation LearningCode1
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
Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse DataCode1
Masked Student Dataset of ExpressionsCode0
Continual Detection Transformer for Incremental Object Detection—0
DiGA: Distil to Generalize and then Adapt for Domain Adaptive Semantic SegmentationCode1
Towards Efficient Task-Driven Model Reprogramming with Foundation Models—0
Self-Distillation for Gaussian Process Regression and ClassificationCode0
MadEye: Boosting Live Video Analytics Accuracy with Adaptive Camera Configurations—0
Selective Knowledge Sharing for Privacy-Preserving Federated Distillation without A Good TeacherCode1
Cross-Class Feature Augmentation for Class Incremental Learning—0
Knowledge-Distilled Graph Neural Networks for Personalized Epileptic Seizure Detection—0
Vision-Language Models for Vision Tasks: A SurveyCode4
Domain Generalization for Crop Segmentation with Standardized Ensemble Knowledge DistillationCode0
A Unified Compression Framework for Efficient Speech-Driven Talking-Face Generation—0
Selective Knowledge Distillation for Non-Autoregressive Neural Machine Translation—0
Quick Dense Retrievers Consume KALE: Post Training Kullback Leibler Alignment of Embeddings for Asymmetrical dual encoders—0
GVP: Generative Volumetric Primitives—0
Knowledge Distillation for Feature Extraction in Underwater VSLAMCode1
oBERTa: Improving Sparse Transfer Learning via improved initialization, distillation, and pruning regimes—0
If At First You Don't Succeed: Test Time Re-ranking for Zero-shot, Cross-domain Retrieval—0
Kaizen: Practical Self-supervised Continual Learning with Continual Fine-tuningCode1
KD-DLGAN: Data Limited Image Generation via Knowledge Distillation—0
Asymmetric Image Retrieval with Cross Model Compatible Ensembles—0
SimDistill: Simulated Multi-modal Distillation for BEV 3D Object DetectionCode1
Dice Semimetric Losses: Optimizing the Dice Score with Soft LabelsCode1
Information-Theoretic GAN Compression with Variational Energy-based Model—0
HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language ModelsCode1
SELF-VS: Self-supervised Encoding Learning For Video SummarizationCode0
Projected Latent Distillation for Data-Agnostic Consolidation in Distributed Continual LearningCode0
DisWOT: Student Architecture Search for Distillation WithOut TrainingCode1
Improving Neural Topic Models with Wasserstein Knowledge DistillationCode0
Show:102550
← PrevPage 41 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