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 3951–4000 of 4240 papers

TitleStatusHype
MSE-Optimal Neural Network Initialization via Layer FusionCode0
Developing Multi-Task Recommendations with Long-Term Rewards via Policy Distilled Reinforcement Learning—0
Generation-Distillation for Efficient Natural Language Understanding in Low-Data Settings—0
Data Techniques For Online End-to-end Speech Recognition—0
Lightweight 3D Human Pose Estimation Network Training Using Teacher-Student Learning—0
A "Network Pruning Network" Approach to Deep Model Compression—0
Uncertainty-Aware Multi-Shot Knowledge Distillation for Image-Based Object Re-Identification—0
Noisy Machines: Understanding Noisy Neural Networks and Enhancing Robustness to Analog Hardware Errors Using Distillation—0
AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture SearchCode0
Unpaired Multi-modal Segmentation via Knowledge DistillationCode1
Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed ClassificationCode1
Learning Task-Agnostic Embedding of Multiple Black-Box Experts for Multi-Task Model Fusion—0
Modeling Teacher-Student Techniques in Deep Neural Networks for Knowledge Distillation—0
DeGAN : Data-Enriching GAN for Retrieving Representative Samples from a Trained Classifier—0
Data-Free Adversarial DistillationCode0
The State of Knowledge Distillation for ClassificationCode0
Joint Architecture and Knowledge Distillation in CNN for Chinese Text Recognition—0
Iterative Dual Domain Adaptation for Neural Machine Translation—0
Explaining Sequence-Level Knowledge Distillation as Data-Augmentation for Neural Machine Translation—0
Acquiring Knowledge from Pre-trained Model to Neural Machine Translation—0
QUEST: Quantized embedding space for transferring knowledgeCode0
Efficient Convolutional Neural Networks for Depth-Based Multi-Person Pose Estimation—0
Online Knowledge Distillation with Diverse PeersCode0
Random Path Selection for Continual LearningCode0
Knowledge Extraction with No Observable DataCode0
Distributed Soft Actor-Critic with Multivariate Reward Representation and Knowledge DistillationCode0
Towards Oracle Knowledge Distillation with Neural Architecture Search—0
Blockwisely Supervised Neural Architecture Search with Knowledge DistillationCode1
QKD: Quantization-aware Knowledge Distillation—0
Data-Driven Compression of Convolutional Neural Networks—0
Hearing Lips: Improving Lip Reading by Distilling Speech Recognizers—0
Go From the General to the Particular: Multi-Domain Translation with Domain Transformation NetworksCode1
Few Shot Network Compression via Cross DistillationCode0
Search to Distill: Pearls are Everywhere but not the Eyes—0
Neural Network Pruning with Residual-Connections and Limited-DataCode0
Towards Making Deep Transfer Learning Never Hurt—0
Preparing Lessons: Improve Knowledge Distillation with Better SupervisionCode1
Maintaining Discrimination and Fairness in Class Incremental LearningCode1
Data Efficient Stagewise Knowledge DistillationCode0
Knowledge Representing: Efficient, Sparse Representation of Prior Knowledge for Knowledge Distillation—0
Learning from a Teacher using Unlabeled DataCode1
Collaborative Distillation for Top-N Recommendation—0
Knowledge Distillation in Document Retrieval—0
Graph Representation Learning via Multi-task Knowledge Distillation—0
Scalable Zero-shot Entity Linking with Dense Entity RetrievalCode2
MKD: a Multi-Task Knowledge Distillation Approach for Pretrained Language Models—0
Knowledge Distillation for Incremental Learning in Semantic Segmentation—0
Deep geometric knowledge distillation with graphsCode0
Microsoft Research Asia's Systems for WMT19—0
Teacher-Student Training for Robust Tacotron-based TTS—0
Show:102550
← PrevPage 80 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