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 1751–1800 of 4240 papers

TitleStatusHype
An Efficient Method of Training Small Models for Regression Problems with Knowledge Distillation—0
DiffusionTalker: Personalization and Acceleration for Speech-Driven 3D Face Diffuser—0
Towards Complementary Knowledge Distillation for Efficient Dense Image Prediction—0
Diffusion-Augmented Coreset Expansion for Scalable Dataset Distillation—0
Improving Neural Ranking via Lossless Knowledge Distillation—0
Diffusion Glancing Transformer for Parallel Sequence to Sequence Learning—0
Differentiable Feature Aggregation Search for Knowledge Distillation—0
DiDOTS: Knowledge Distillation from Large-Language-Models for Dementia Obfuscation in Transcribed Speech—0
An Efficient Federated Distillation Learning System for Multi-task Time Series Classification—0
Add a SideNet to your MainNet—0
Bootstrapping Chest CT Image Understanding by Distilling Knowledge from X-ray Expert Models—0
DFM: Dialogue Foundation Model for Universal Large-Scale Dialogue-Oriented Task Learning—0
Bootstrapped Representation Learning for Skeleton-Based Action Recognition—0
An Efficient Detection and Control System for Underwater Docking using Machine Learning and Realistic Simulation: A Comprehensive Approach—0
Dialect Identification through Adversarial Learning and Knowledge Distillation on Romanian BERT—0
DiagrammaticLearning: A Graphical Language for Compositional Training Regimes—0
BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping—0
DFRD: Data-Free Robustness Distillation for Heterogeneous Federated Learning—0
Boost Vision Transformer with GPU-Friendly Sparsity and Quantization—0
An Efficient Active Learning Pipeline for Legal Text Classification—0
DFMSD: Dual Feature Masking Stage-wise Knowledge Distillation for Object Detection—0
DeViT: Decomposing Vision Transformers for Collaborative Inference in Edge Devices—0
Device-Directed Speech Detection: Regularization via Distillation for Weakly-Supervised Models—0
Boosting Self-Supervision for Single-View Scene Completion via Knowledge Distillation—0
Developing Multi-Task Recommendations with Long-Term Rewards via Policy Distilled Reinforcement Learning—0
DETRDistill: A Universal Knowledge Distillation Framework for DETR-families—0
Detecting Optimism in Tweets using Knowledge Distillation and Linguistic Analysis of Optimism—0
An Effective Deep Network for Head Pose Estimation without Keypoints—0
Analyzing the Importance of Blank for CTC-Based Knowledge Distillation—0
A Cohesive Distillation Architecture for Neural Language Models—0
DistillGrasp: Integrating Features Correlation with Knowledge Distillation for Depth Completion of Transparent Objects—0
Designing Parameter and Compute Efficient Diffusion Transformers using Distillation—0
Designing an Improved Deep Learning-based Model for COVID-19 Recognition in Chest X-ray Images: A Knowledge Distillation Approach—0
Designing and Training of Lightweight Neural Networks on Edge Devices using Early Halting in Knowledge Distillation—0
Boosting Lossless Speculative Decoding via Feature Sampling and Partial Alignment Distillation—0
DεpS: Delayed ε-Shrinking for Faster Once-For-All Training—0
Deploying a BERT-based Query-Title Relevance Classifier in a Production System: a View from the Trenches—0
Boosting Graph Neural Networks via Adaptive Knowledge Distillation—0
Analyzing Knowledge Distillation in Neural Machine Translation—0
Densely Distilling Cumulative Knowledge for Continual Learning—0
Boosting Contrastive Learning with Relation Knowledge Distillation—0
Denoising Mutual Knowledge Distillation in Bi-Directional Multiple Instance Learning—0
BoostingBERT:Integrating Multi-Class Boosting into BERT for NLP Tasks—0
Analyzing Compression Techniques for Computer Vision—0
Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detector—0
Delving Deep into Semantic Relation Distillation—0
Boosting Accuracy and Robustness of Student Models via Adaptive Adversarial Distillation—0
BOLT: Bootstrap Long Chain-of-Thought in Language Models without Distillation—0
An Active Learning Framework for Inclusive Generation by Large Language Models—0
Adaptive Regularization of Labels—0
Show:102550
← PrevPage 36 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