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 3151–3200 of 4240 papers

TitleStatusHype
Peer Collaborative Learning for Polyphonic Sound Event Detection—0
Knowledge Distillation for Neural Transducers from Large Self-Supervised Pre-trained Models—0
Towards Accurate Cross-Domain In-Bed Human Pose EstimationCode1
Inter-Domain Alignment for Predicting High-Resolution Brain Networks Using Teacher-Student LearningCode0
Online Hyperparameter Meta-Learning with Hypergradient Distillation—0
KNOT: Knowledge Distillation using Optimal Transport for Solving NLP TasksCode1
On the Interplay Between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis—0
Student Helping Teacher: Teacher Evolution via Self-Knowledge DistillationCode0
Multilingual AMR Parsing with Noisy Knowledge DistillationCode1
Prune Your Model Before Distill ItCode1
Improving Neural Ranking via Lossless Knowledge Distillation—0
Deep Neural Compression Via Concurrent Pruning and Self-Distillation—0
A Comprehensive Overhaul of Distilling Unconditional GANs—0
Prototypical Contrastive Predictive Coding—0
Self-supervised Models are Good Teaching Assistants for Vision Transformers—0
A Unified Knowledge Distillation Framework for Deep Directed Graphical Models—0
Not All Regions are Worthy to be Distilled: Region-aware Knowledge Distillation Towards Efficient Image-to-Image Translation—0
Explaining Knowledge Graph Embedding via Latent Rule Learning—0
Adaptive Label Smoothing with Self-Knowledge—0
Automated Channel Pruning with Learned Importance—0
Distilling GANs with Style-Mixed Triplets for X2I Translation with Limited Data—0
Stingy Teacher: Sparse Logits Suffice to Fail Knowledge Distillation—0
MOBA: Multi-teacher Model Based Reinforcement Learning—0
Fast and Efficient Once-For-All Networks for Diverse Hardware Deployment—0
Generate, Annotate, and Learn: Generative Models Advance Self-Training and Knowledge Distillation—0
Neural Architecture Search via Ensemble-based Knowledge Distillation—0
Wakening Past Concepts without Past Data: Class-incremental Learning from Placebos—0
Understanding the Success of Knowledge Distillation -- A Data Augmentation Perspective—0
Learning Efficient Image Super-Resolution Networks via Structure-Regularized Pruning—0
Representation Consolidation from Multiple Expert Teachers—0
Self-Slimming Vision Transformer—0
Self-Distilled Pruning Of Neural Networks—0
SeqPATE: Differentially Private Text Generation via Knowledge Distillation—0
Reducing the Teacher-Student Gap via Adaptive Temperatures—0
Source-Target Unified Knowledge Distillation for Memory-Efficient Federated Domain Adaptation on Edge Devices—0
Pseudo Knowledge Distillation: Towards Learning Optimal Instance-specific Label Smoothing Regularization—0
Feature Kernel Distillation—0
Scaling Fair Learning to Hundreds of Intersectional Groups—0
Exploiting Knowledge Distillation for Few-Shot Image Generation—0
To Smooth or not to Smooth? On Compatibility between Label Smoothing and Knowledge Distillation—0
Convolutional Neural Network Compression through Generalized Kronecker Product Decomposition—0
Deep Structured Instance Graph for Distilling Object DetectorsCode1
Improving Question Answering Performance Using Knowledge Distillation and Active LearningCode0
Partial to Whole Knowledge Distillation: Progressive Distilling Decomposed Knowledge Boosts Student Better—0
Dynamic Knowledge Distillation for Pre-trained Language ModelsCode1
Recent Advances of Continual Learning in Computer Vision: An Overview—0
Low-Latency Incremental Text-to-Speech Synthesis with Distilled Context Prediction Network—0
The NiuTrans Machine Translation Systems for WMT21—0
K-AID: Enhancing Pre-trained Language Models with Domain Knowledge for Question Answering—0
KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge DistillationCode0
Show:102550
← PrevPage 64 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