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 3651–3700 of 4240 papers

TitleStatusHype
Federated Knowledge DistillationCode1
Paralinguistic Privacy Protection at the Edge—0
On Self-Distilling Graph Neural Network—0
Channel Planting for Deep Neural Networks using Knowledge Distillation—0
Domain Adaptive Knowledge Distillation for Driving Scene Semantic SegmentationCode1
A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks—0
Distilling Knowledge by Mimicking FeaturesCode0
Data-free Knowledge Distillation for Segmentation using Data-Enriching GANCode0
Learning to Maximize Speech Quality Directly Using MOS Prediction for Neural Text-to-Speech—0
HW-TSC’s Participation in the WMT 2020 News Translation Shared Task—0
The NiuTrans Machine Translation Systems for WMT20—0
IIE’s Neural Machine Translation Systems for WMT20—0
High Performance Natural Language Processing—0
Fast End-to-end Coreference Resolution for Korean—0
Using the Past Knowledge to Improve Sentiment Classification—0
FedED: Federated Learning via Ensemble Distillation for Medical Relation Extraction—0
Bridging the Gap between Prior and Posterior Knowledge Selection for Knowledge-Grounded Dialogue Generation—0
Distilling Structured Knowledge for Text-Based Relational Reasoning—0
MixKD: Towards Efficient Distillation of Large-scale Language Models—0
ProxylessKD: Direct Knowledge Distillation with Inherited Classifier for Face Recognition—0
Cross-lingual Machine Reading Comprehension with Language Branch Knowledge Distillation—0
Activation Map Adaptation for Effective Knowledge Distillation—0
FastFormers: Highly Efficient Transformer Models for Natural Language UnderstandingCode1
Empowering Knowledge Distillation via Open Set Recognition for Robust 3D Point Cloud Classification—0
Two-stage Textual Knowledge Distillation for End-to-End Spoken Language UnderstandingCode0
Multi-Task Learning with Shared Encoder for Non-Autoregressive Machine TranslationCode1
Pre-trained Summarization DistillationCode0
Improved Synthetic Training for Reading Comprehension—0
Iterative Graph Self-Distillation—0
Generating Long Financial Report using Conditional Variational Autoencoders with Knowledge Distillation—0
Distilling Dense Representations for Ranking using Tightly-Coupled TeachersCode1
Knowledge Distillation for BERT Unsupervised Domain AdaptationCode1
Knowledge Distillation for Improved Accuracy in Spoken Question Answering—0
Contextualized Attention-based Knowledge Transfer for Spoken Conversational Question Answering—0
Fast Video Salient Object Detection via Spatiotemporal Knowledge Distillation—0
Knowledge Distillation in Wide Neural Networks: Risk Bound, Data Efficiency and Imperfect Teacher—0
Edge Bias in Federated Learning and its Solution by Buffered Knowledge Distillation—0
Noisy Neural Network Compression for Analog Storage Devices—0
Comparing Fisher Information Regularization with Distillation for DNN Quantization—0
Infusing Sequential Information into Conditional Masked Translation Model with Self-Review MechanismCode0
Reducing the Teacher-Student Gap via Spherical Knowledge DisitllationCode1
Task Decoupled Knowledge Distillation For Lightweight Face DetectorsCode1
AutoADR: Automatic Model Design for Ad Relevance—0
MulDE: Multi-teacher Knowledge Distillation for Low-dimensional Knowledge Graph Embeddings—0
Dual-mode ASR: Unify and Improve Streaming ASR with Full-context Modeling—0
Collective Wisdom: Improving Low-resource Neural Machine Translation using Adaptive Knowledge Distillation—0
Structural Knowledge Distillation: Tractably Distilling Information for Structured PredictorCode0
Adversarial Self-Supervised Data-Free Distillation for Text Classification—0
Distilling a Deep Neural Network into a Takagi-Sugeno-Kang Fuzzy Inference System—0
Locally Linear Region Knowledge Distillation—0
Show:102550
← PrevPage 74 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