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 1551–1600 of 4240 papers

TitleStatusHype
CDFKD-MFS: Collaborative Data-free Knowledge Distillation via Multi-level Feature SharingCode0
An Unsupervised Multiple-Task and Multiple-Teacher Model for Cross-lingual Named Entity RecognitionCode0
HiTSR: A Hierarchical Transformer for Reference-based Super-ResolutionCode0
CoReD: Generalizing Fake Media Detection with Continual Representation using DistillationCode0
Highlight Every Step: Knowledge Distillation via Collaborative TeachingCode0
Dynamic Data-Free Knowledge Distillation by Easy-to-Hard Learning StrategyCode0
PyNET-QxQ: An Efficient PyNET Variant for QxQ Bayer Pattern Demosaicing in CMOS Image SensorsCode0
Distilling Stereo Networks for Performant and Efficient Leaner NetworksCode0
Handling Data Heterogeneity in Federated Learning via Knowledge Distillation and FusionCode0
HDKD: Hybrid Data-Efficient Knowledge Distillation Network for Medical Image ClassificationCode0
Correlation Congruence for Knowledge DistillationCode0
GSB: Group Superposition Binarization for Vision Transformer with Limited Training SamplesCode0
Group Multi-View Transformer for 3D Shape Analysis with Spatial EncodingCode0
Feature Fusion for Online Mutual Knowledge DistillationCode0
GSSF: Generalized Structural Sparse Function for Deep Cross-modal Metric LearningCode0
Guiding Frame-Level CTC Alignments Using Self-knowledge DistillationCode0
Answering Diverse Questions via Text Attached with Key Audio-Visual CluesCode0
Distilling Object Detectors With Global KnowledgeCode0
Greedy-layer Pruning: Speeding up Transformer Models for Natural Language ProcessingCode0
Feature Representation Learning for Robust Retinal Disease Detection from Optical Coherence Tomography ImagesCode0
Distilling Object Detectors with Fine-grained Feature ImitationCode0
Catch-Up Distillation: You Only Need to Train Once for Accelerating SamplingCode0
Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge DistillationCode0
Graph Knowledge Distillation to Mixture of ExpertsCode0
Distilling Reasoning Capabilities into Smaller Language ModelsCode0
FedBKD: Distilled Federated Learning to Embrace Gerneralization and Personalization on Non-IID DataCode0
FedBrain-Distill: Communication-Efficient Federated Brain Tumor Classification Using Ensemble Knowledge Distillation on Non-IID DataCode0
Graph-based Knowledge Distillation by Multi-head Attention NetworkCode0
Gradient Knowledge Distillation for Pre-trained Language ModelsCode0
Graph Entropy Minimization for Semi-supervised Node ClassificationCode0
Distilling Model KnowledgeCode0
Class incremental learning with probability dampening and cascaded gated classifierCode0
Distilling Local Texture Features for Colorectal Tissue Classification in Low Data RegimesCode0
GOTHAM: Graph Class Incremental Learning Framework under Weak SupervisionCode0
FedDW: Distilling Weights through Consistency Optimization in Heterogeneous Federated LearningCode0
LIDAR and Position-Aided mmWave Beam Selection with Non-local CNNs and Curriculum TrainingCode0
Reinforced Knowledge Distillation for Time Series RegressionCode0
Rejuvenating Low-Frequency Words: Making the Most of Parallel Data in Non-Autoregressive TranslationCode0
Goal-Conditioned Q-Learning as Knowledge DistillationCode0
Goldfish: An Efficient Federated Unlearning FrameworkCode0
CaPriDe Learning: Confidential and Private Decentralized Learning Based on Encryption-Friendly Distillation LossCode0
A Diversity-Enhanced Knowledge Distillation Model for Practical Math Word Problem SolvingCode0
GNN's Uncertainty Quantification using Self-DistillationCode0
Spending Your Winning Lottery Better After Drawing ItCode0
Improved Knowledge Distillation for Crowd Counting on IoT DeviceCode0
Federated Incremental Named Entity RecognitionCode0
CAPEEN: Image Captioning with Early Exits and Knowledge DistillationCode0
GKD: Semi-supervised Graph Knowledge Distillation for Graph-Independent InferenceCode0
GKT: A Novel Guidance-Based Knowledge Transfer Framework For Efficient Cloud-edge Collaboration LLM DeploymentCode0
Generative Denoise Distillation: Simple Stochastic Noises Induce Efficient Knowledge Transfer for Dense PredictionCode0
Show:102550
← PrevPage 32 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