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 3501–3550 of 4240 papers

TitleStatusHype
Large-Scale Data-Free Knowledge Distillation for ImageNet via Multi-Resolution Data GenerationCode0
Learning from Noisy Crowd Labels with LogicsCode0
Language-Universal Adapter Learning with Knowledge Distillation for End-to-End Multilingual Speech RecognitionCode0
Pre-trained Summarization DistillationCode0
Efficient and Robust Jet Tagging at the LHC with Knowledge DistillationCode0
SeqMIA: Sequential-Metric Based Membership Inference AttackCode0
SeqNAS: Neural Architecture Search for Event Sequence ClassificationCode0
Learning Lightweight Lane Detection CNNs by Self Attention DistillationCode0
UniTrans: Unifying Model Transfer and Data Transfer for Cross-Lingual Named Entity Recognition with Unlabeled DataCode0
Contrastive Learning in Distilled ModelsCode0
Language Model Knowledge Distillation for Efficient Question Answering in SpanishCode0
Contrastive Conditioning for Assessing Disambiguation in MT: A Case Study of Distilled BiasCode0
KS-DETR: Knowledge Sharing in Attention Learning for Detection TransformerCode0
Knowledge Transfer Graph for Deep Collaborative LearningCode0
Text Representation Distillation via Information Bottleneck PrincipleCode0
KnowledgeSG: Privacy-Preserving Synthetic Text Generation with Knowledge Distillation from ServerCode0
Online Lifelong Generalized Zero-Shot LearningCode0
Adaptive Temperature Based on Logits Correlation in Knowledge DistillationCode0
Improving Sequential Recommendations via Bidirectional Temporal Data Augmentation with Pre-trainingCode0
Continual Representation Learning for Biometric IdentificationCode0
Continual Panoptic Perception: Towards Multi-modal Incremental Interpretation of Remote Sensing ImagesCode0
Privacy Evaluation Benchmarks for NLP ModelsCode0
Knowledge Grafting of Large Language ModelsCode0
Knowledge Extraction with No Observable DataCode0
Learning to Maximize Mutual Information for Chain-of-Thought DistillationCode0
Knowledge Distillation with Reptile Meta-Learning for Pretrained Language Model CompressionCode0
Privacy in Practice: Private COVID-19 Detection in X-Ray Images (Extended Version)Code0
Privacy-preserving Early Detection of Epileptic Seizures in VideosCode0
The Curious Case of Hallucinations in Neural Machine TranslationCode0
Knowledge Distillation with Adversarial Samples Supporting Decision BoundaryCode0
Learning to "Segment Anything" in Thermal Infrared Images through Knowledge Distillation with a Large Scale Dataset SATIRCode0
The Devil is in the Data: Learning Fair Graph Neural Networks via Partial Knowledge DistillationCode0
SFT-KD-Recon: Learning a Student-friendly Teacher for Knowledge Distillation in Magnetic Resonance Image ReconstructionCode0
SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image ClassificationCode0
Shape-intensity knowledge distillation for robust medical image segmentationCode0
Bridging the Sim-to-Real Gap from the Information Bottleneck PerspectiveCode0
Assessor-Guided Learning for Continual EnvironmentsCode0
Shapeshifter: a Parameter-efficient Transformer using Factorized Reshaped MatricesCode0
Learning without Forgetting for 3D Point Cloud ObjectsCode0
Are All Linear Regions Created Equal?Code0
Vision Transformers for Small Histological Datasets Learned through Knowledge DistillationCode0
Learn What Is Possible, Then Choose What Is Best: Disentangling One-To-Many Relations in Language Through Text-based GamesCode0
Continual Knowledge Distillation for Neural Machine TranslationCode0
Leave No One Behind: Enhancing Diversity While Maintaining Accuracy in Social RecommendationCode0
Words Matter: Leveraging Individual Text Embeddings for Code Generation in CLIP Test-Time AdaptationCode0
EaSyGuide : ESG Issue Identification Framework leveraging Abilities of Generative Large Language ModelsCode0
LENAS: Learning-based Neural Architecture Search and Ensemble for 3D Radiotherapy Dose PredictionCode0
Knowledge Distillation via Instance Relationship GraphCode0
Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog SystemsCode0
Knowledge distillation to effectively attain both region-of-interest and global semantics from an image where multiple objects appearCode0
Show:102550
← PrevPage 71 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