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 4051–4100 of 4240 papers

TitleStatusHype
Revisiting Knowledge Distillation via Label Smoothing RegularizationCode0
XD: Cross-lingual Knowledge Distillation for Polyglot Sentence Embeddings—0
Extremely Small BERT Models from Mixed-Vocabulary Training—0
Technical report on Conversational Question Answering—0
FEED: Feature-level Ensemble for Knowledge Distillation—0
TinyBERT: Distilling BERT for Natural Language UnderstandingCode0
Learning Lightweight Pedestrian Detector with Hierarchical Knowledge Distillation—0
Ensemble Knowledge Distillation for Learning Improved and Efficient NetworksCode0
Knowledge Transfer Graph for Deep Collaborative LearningCode0
Accelerating Transformer Decoding via a Hybrid of Self-attention and Recurrent Neural Network—0
Knowledge distillation for optimization of quantized deep neural networks—0
Knowledge Distillation for End-to-End Person SearchCode0
Online Sensor Hallucination via Knowledge Distillation for Multimodal Image Classification—0
Patient Knowledge Distillation for BERT Model CompressionCode0
Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement—0
Language Graph Distillation for Low-Resource Machine Translation—0
Knowledge distillation for semi-supervised domain adaptation—0
Adaptive Regularization of Labels—0
Scalable Attentive Sentence-Pair Modeling via Distilled Sentence EmbeddingCode0
Effective Training of Convolutional Neural Networks with Low-bitwidth Weights and Activations—0
Knowledge Consistency between Neural Networks and Beyond—0
Learning Lightweight Lane Detection CNNs by Self Attention DistillationCode0
Self-Knowledge Distillation in Natural Language Processing—0
GTCOM Neural Machine Translation Systems for WMT19—0
The NiuTrans Machine Translation Systems for WMT19—0
Baidu Neural Machine Translation Systems for WMT19—0
PANLP at MEDIQA 2019: Pre-trained Language Models, Transfer Learning and Knowledge Distillation—0
Distill-to-Label: Weakly Supervised Instance Labeling Using Knowledge Distillation—0
Distilled Siamese Networks for Visual Tracking—0
Highlight Every Step: Knowledge Distillation via Collaborative TeachingCode0
Real-Time Correlation Tracking via Joint Model Compression and TransferCode0
Lifelong GAN: Continual Learning for Conditional Image Generation—0
Similarity-Preserving Knowledge Distillation—0
Light Multi-segment Activation for Model CompressionCode0
Learn Spelling from Teachers: Transferring Knowledge from Language Models to Sequence-to-Sequence Speech Recognition—0
BAM! Born-Again Multi-Task Networks for Natural Language UnderstandingCode0
Graph-based Knowledge Distillation by Multi-head Attention NetworkCode0
Compression of Acoustic Event Detection Models With Quantized Distillation—0
Reconstructing Perceived Images from Brain Activity by Visually-guided Cognitive Representation and Adversarial Learning—0
Essence Knowledge Distillation for Speech Recognition—0
Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog SystemsCode0
GAN-Knowledge Distillation for one-stage Object Detection—0
Membership Privacy for Machine Learning Models Through Knowledge Transfer—0
Divide and Conquer: Leveraging Intermediate Feature Representations for Quantized Training of Neural Networks—0
Scalable Syntax-Aware Language Models Using Knowledge Distillation—0
Efficient Evaluation-Time Uncertainty Estimation by Improved Distillation—0
Incremental Classifier Learning Based on PEDCC-Loss and Cosine Distance—0
Distilling Object Detectors with Fine-grained Feature ImitationCode0
Private Deep Learning with Teacher Ensembles—0
Deep Face Recognition Model Compression via Knowledge Transfer and Distillation—0
Show:102550
← PrevPage 82 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