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 751–800 of 4240 papers

TitleStatusHype
EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge DistillationCode1
Improving Knowledge Distillation via Category StructureCode1
Initialization and Regularization of Factorized Neural LayersCode1
CTC-based Non-autoregressive Textless Speech-to-Speech TranslationCode1
AIM 2024 Challenge on UHD Blind Photo Quality AssessmentCode1
Expanding Scene Graph Boundaries: Fully Open-vocabulary Scene Graph Generation via Visual-Concept Alignment and RetentionCode1
Evolving Search Space for Neural Architecture SearchCode1
Contrastive Deep SupervisionCode1
Contrastive Distillation on Intermediate Representations for Language Model CompressionCode1
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot LearningCode1
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?Code1
Contrastive Model Inversion for Data-Free Knowledge DistillationCode1
Contrastive Representation DistillationCode1
AutoGAN-Distiller: Searching to Compress Generative Adversarial NetworksCode1
Exploring Inter-Channel Correlation for Diversity-preserved KnowledgeDistillationCode1
Exploring Inter-Channel Correlation for Diversity-Preserved Knowledge DistillationCode1
AdaptGuard: Defending Against Universal Attacks for Model AdaptationCode1
The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single ImageCode1
FitNets: Hints for Thin Deep NetsCode1
Generic-to-Specific Distillation of Masked AutoencodersCode1
FairDistillation: Mitigating Stereotyping in Language ModelsCode1
CaMEL: Mean Teacher Learning for Image CaptioningCode1
Improve Object Detection with Feature-based Knowledge Distillation: Towards Accurate and Efficient DetectorsCode1
CaKDP: Category-aware Knowledge Distillation and Pruning Framework for Lightweight 3D Object DetectionCode1
FAMIE: A Fast Active Learning Framework for Multilingual Information ExtractionCode1
Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary CellsCode1
One Step Diffusion-based Super-Resolution with Time-Aware DistillationCode1
One-Step Knowledge Distillation and Fine-Tuning in Using Large Pre-Trained Self-Supervised Learning Models for Speaker VerificationCode1
Cumulative Spatial Knowledge Distillation for Vision TransformersCode1
FastFormers: Highly Efficient Transformer Models for Natural Language UnderstandingCode1
Faster ILOD: Incremental Learning for Object Detectors based on Faster RCNNCode1
Online Knowledge Distillation for Efficient Pose EstimationCode1
Improved Techniques for Training Adaptive Deep NetworksCode1
Fast-Vid2Vid: Spatial-Temporal Compression for Video-to-Video SynthesisCode1
FDCNet: Feature Drift Compensation Network for Class-Incremental Weakly Supervised Object LocalizationCode1
FCS: Feature Calibration and Separation for Non-Exemplar Class Incremental LearningCode1
Avatar Knowledge Distillation: Self-ensemble Teacher Paradigm with UncertaintyCode1
On Representation Knowledge Distillation for Graph Neural NetworksCode1
A Knowledge Distillation Framework For Enhancing Ear-EEG Based Sleep Staging With Scalp-EEG DataCode1
Improving Continual Relation Extraction by Distinguishing Analogous SemanticsCode1
Implicit Chain of Thought Reasoning via Knowledge DistillationCode1
FedACK: Federated Adversarial Contrastive Knowledge Distillation for Cross-Lingual and Cross-Model Social Bot DetectionCode1
FedDAT: An Approach for Foundation Model Finetuning in Multi-Modal Heterogeneous Federated LearningCode1
FedCL: Federated Multi-Phase Curriculum Learning to Synchronously Correlate User HeterogeneityCode1
Curriculum Learning for Dense Retrieval DistillationCode1
Creating Something from Nothing: Unsupervised Knowledge Distillation for Cross-Modal HashingCode1
Federated Knowledge DistillationCode1
KNOT: Knowledge Distillation using Optimal Transport for Solving NLP TasksCode1
FedMD: Heterogenous Federated Learning via Model DistillationCode1
Improve Cross-Architecture Generalization on Dataset DistillationCode1
Show:102550
← PrevPage 16 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