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 3301–3350 of 4240 papers

TitleStatusHype
FedRAD: Federated Robust Adaptive Distillation—0
Shapeshifter: a Parameter-efficient Transformer using Factorized Reshaped MatricesCode0
Unsupervised Representation Transfer for Small Networks: I Believe I Can Distill On-the-Fly—0
Handling Long-tailed Feature Distribution in AdderNets—0
Analyzing the Confidentiality of Undistillable Teachers in Knowledge DistillationCode0
Adversarial Teacher-Student Representation Learning for Domain GeneralizationCode0
Using a GAN to Generate Adversarial Examples to Facial Image Recognition—0
Improved Knowledge Distillation via Adversarial Collaboration—0
Efficient Federated Learning for AIoT Applications Using Knowledge Distillation—0
ESGN: Efficient Stereo Geometry Network for Fast 3D Object Detection—0
Ensembling of Distilled Models from Multi-task Teachers for Constrained Resource Language Pairs—0
Domain-Agnostic Clustering with Self-Distillation—0
Semi-Online Knowledge DistillationCode0
Local-Selective Feature Distillation for Single Image Super-Resolution—0
Contrast-reconstruction Representation Learning for Self-supervised Skeleton-based Action Recognition—0
Hierarchical Knowledge Distillation for Dialogue Sequence Labeling—0
Teacher-Student Training and Triplet Loss to Reduce the Effect of Drastic Face Occlusion—0
Toxicity Detection can be Sensitive to the Conversational Context—0
Dynamically pruning segformer for efficient semantic segmentation—0
Hierarchical Knowledge Guided Learning for Real-world Retinal Diseases Recognition—0
One General Teacher for Multi-Data Multi-Task: A New Knowledge Distillation Framework for Discourse Relation Analysis—0
Redistributing Low-Frequency Words: Making the Most of Monolingual Data in Non-Autoregressive Translation—0
NVIDIA NeMo Neural Machine Translation Systems for English-German and English-Russian News and Biomedical Tasks at WMT21—0
Feature Structure Distillation for BERT Transferring—0
An Unsupervised Multiple-Task and Multiple-Teacher Model for Cross-lingual Named Entity RecognitionCode0
Multi-stage Distillation Framework for Cross-Lingual Semantic Similarity Matching—0
Learning to Teach with Student Feedback—0
Multi-Granularity Contrastive Knowledge Distillation for Multimodal Named Entity Recognition—0
Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation—0
Deep-to-bottom Weights Decay: A Systemic Knowledge Review Learning Technique for Transformer Layers in Knowledge Distillation—0
Self-Distilled Pruning of Neural Networks—0
When Chosen Wisely, More Data Is What You Need: A Universal Sample-Efficient Strategy For Data Augmentation—0
Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm—0
Making Small Language Models Better Few-Shot Learners—0
Aligned Weight Regularizers for Pruning Pretrained Neural Networks—0
A Flexible Multi-Task Model for BERT Serving—0
Compositional Data Augmentation for Abstractive Conversation Summarization—0
Synthetic Unknown Class Learning for Learning Unknowns—0
Robust and Accurate Object Detection via Self-Knowledge DistillationCode0
Facial Landmark Points Detection Using Knowledge Distillation-Based Neural NetworksCode0
Domain Generalization on Efficient Acoustic Scene Classification using Residual Normalization—0
Learning Interpretation with Explainable Knowledge Distillation—0
Incremental Meta-Learning via Episodic Replay Distillation for Few-Shot Image RecognitionCode0
A Survey on Green Deep Learning—0
Class Token and Knowledge Distillation for Multi-head Self-Attention Speaker Verification Systems—0
AUTOKD: Automatic Knowledge Distillation Into A Student Architecture Family—0
Visualizing the Emergence of Intermediate Visual Patterns in DNNs—0
Oracle Teacher: Leveraging Target Information for Better Knowledge Distillation of CTC Models—0
A methodology for training homomorphicencryption friendly neural networks—0
DVFL: A Vertical Federated Learning Method for Dynamic Data—0
Show:102550
← PrevPage 67 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