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 3551–3600 of 4240 papers

TitleStatusHype
Adversarially Robust and Explainable Model Compression with On-Device Personalization for Text Classification—0
Spending Your Winning Lottery Better After Drawing ItCode0
Knowledge Distillation in Iterative Generative Models for Improved Sampling SpeedCode1
MSD: Saliency-aware Knowledge Distillation for Multimodal Understanding—0
Label Augmentation via Time-based Knowledge Distillation for Financial Anomaly Detection—0
Self-Mutual Distillation Learning for Continuous Sign Language RecognitionCode1
FLAR: A Unified Prototype Framework for Few-Sample Lifelong Active Recognition—0
Unpaired Learning for Deep Image Deraining With Rain Direction Regularizer—0
Kernel Methods in Hyperbolic Spaces—0
Exploring Inter-Channel Correlation for Diversity-Preserved Knowledge DistillationCode1
Active Learning for Lane Detection: A Knowledge Distillation Approach—0
Student Customized Knowledge Distillation: Bridging the Gap Between Student and Teacher—0
Improving De-Raining Generalization via Neural Reorganization—0
Distilling Global and Local Logits With Densely Connected RelationsCode0
Rethinking Soft Labels for Knowledge Distillation: A Bias–Variance Tradeoff Perspective—0
Disentanglement, Visualization and Analysis of Complex Features in DNNs—0
Improve Object Detection with Feature-based Knowledge Distillation: Towards Accurate and Efficient DetectorsCode1
Can Students Outperform Teachers in Knowledge Distillation based Model Compression?—0
Contextual Knowledge Distillation for Transformer Compression—0
Explicit Connection Distillation—0
Knowledge distillation via softmax regression representation learning—0
Knowledge Distillation based Ensemble Learning for Neural Machine Translation—0
Learning from deep model via exploring local targets—0
Understanding Adversarial Attacks on Autoencoders—0
Long Live the Lottery: The Existence of Winning Tickets in Lifelong Learning—0
Robust Overfitting may be mitigated by properly learned smoothening—0
Don't be picky, all students in the right family can learn from good teachers—0
Understanding Knowledge Distillation—0
Unified Mandarin TTS Front-end Based on Distilled BERT ModelCode1
Towards Zero-Shot Knowledge Distillation for Natural Language Processing—0
Fully Synthetic Data Improves Neural Machine Translation with Knowledge Distillation—0
Knowledge Distillation with Adaptive Asymmetric Label Sharpening for Semi-supervised Fracture Detection in Chest X-rays—0
Understanding and Improving Lexical Choice in Non-Autoregressive Translation—0
CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models CascadeCode1
Learning Light-Weight Translation Models from Deep TransformerCode1
ALP-KD: Attention-Based Layer Projection for Knowledge Distillation—0
Towards a Universal Continuous Knowledge Base—0
Future-Guided Incremental Transformer for Simultaneous Translation—0
AttentionLite: Towards Efficient Self-Attention Models for Vision—0
Diverse Knowledge Distillation for End-to-End Person Search—0
Computation-Efficient Knowledge Distillation via Uncertainty-Aware MixupCode1
Invariant Teacher and Equivariant Student for Unsupervised 3D Human Pose EstimationCode1
Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning—0
Distilling Optimal Neural Networks: Rapid Search in Diverse Spaces—0
Wasserstein Contrastive Representation Distillation—0
LRC-BERT: Latent-representation Contrastive Knowledge Distillation for Natural Language Understanding—0
Periocular Embedding Learning with Consistent Knowledge Distillation from Face—0
Improving Task-Agnostic BERT Distillation with Layer Mapping Search—0
Reinforced Multi-Teacher Selection for Knowledge Distillation—0
Large-Scale Generative Data-Free Distillation—0
Show:102550
← PrevPage 72 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