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 2351–2400 of 4240 papers

TitleStatusHype
Understanding and Improving Knowledge Distillation for Quantization-Aware Training of Large Transformer EncodersCode0
EEG aided boosting of single-lead ECG based sleep staging with Deep Knowledge DistillationCode1
DASECount: Domain-Agnostic Sample-Efficient Wireless Indoor Crowd Counting via Few-shot Learning—0
Is Smaller Always Faster? Tradeoffs in Compressing Self-Supervised Speech TransformersCode0
Knowledge distillation for fast and accurate DNA sequence correction—0
DETRDistill: A Universal Knowledge Distillation Framework for DETR-families—0
ConNER: Consistency Training for Cross-lingual Named Entity RecognitionCode1
Sub-Graph Learning for Spatiotemporal Forecasting via Knowledge Distillation—0
BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object DetectionCode1
D^3ETR: Decoder Distillation for Detection Transformer—0
Yield Evaluation of Citrus Fruits based on the YoloV5 compressed by Knowledge Distillation—0
Knowledge Distillation for Detection Transformer with Consistent Distillation Points SamplingCode0
An Efficient Active Learning Pipeline for Legal Text Classification—0
An Investigation of the Combination of Rehearsal and Knowledge Distillation in Continual Learning for Spoken Language UnderstandingCode0
Instance-aware Model Ensemble With Distillation For Unsupervised Domain Adaptation—0
FedCL: Federated Multi-Phase Curriculum Learning to Synchronously Correlate User HeterogeneityCode1
Feature Correlation-guided Knowledge Transfer for Federated Self-supervised Learning—0
An Interpretable Neuron Embedding for Static Knowledge Distillation—0
Structured Knowledge Distillation Towards Efficient and Compact Multi-View 3D Detection—0
Cross-Modality Knowledge Distillation Network for Monocular 3D Object DetectionCode1
Fcaformer: Forward Cross Attention in Hybrid Vision TransformerCode1
Long-Range Zero-Shot Generative Deep Network Quantization—0
MDFlow: Unsupervised Optical Flow Learning by Reliable Mutual Knowledge DistillationCode1
Knowledge Distillation from Cross Teaching Teachers for Efficient Semi-Supervised Abdominal Organ Segmentation in CTCode0
FAN-Trans: Online Knowledge Distillation for Facial Action Unit Detection—0
PILE: Pairwise Iterative Logits Ensemble for Multi-Teacher Labeled Distillation—0
Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge DistillationCode2
Knowledge Distillation for Federated Learning: a Practical Guide—0
Understanding the Role of Mixup in Knowledge Distillation: An Empirical StudyCode0
Bridging Fairness and Environmental Sustainability in Natural Language Processing—0
CoNMix for Source-free Single and Multi-target Domain AdaptationCode1
AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-TimeCode5
Closing the Gap between Client and Global Model Performance in Heterogeneous Federated Learning—0
Peak-First CTC: Reducing the Peak Latency of CTC Models by Applying Peak-First Regularization—0
Breaking the trade-off in personalized speech enhancement with cross-task knowledge distillation—0
SSDA-YOLO: Semi-supervised Domain Adaptive YOLO for Cross-Domain Object DetectionCode2
LightVessel: Exploring Lightweight Coronary Artery Vessel Segmentation via Similarity Knowledge Distillation—0
MPCFormer: fast, performant and private Transformer inference with MPCCode1
Gradient Knowledge Distillation for Pre-trained Language ModelsCode0
Multi-level Distillation of Semantic Knowledge for Pre-training Multilingual Language Model—0
Fairness without Demographics through Knowledge DistillationCode0
Lightweight Sound Event Detection Model with RepVGG Architecture—0
Enhancing Chinese Multi-Label Text Classification Performance with Response-based Knowledge Distillation—0
Maximum Likelihood Distillation for Robust Modulation Classification—0
ARDIR: Improving Robustness using Knowledge Distillation of Internal Representation—0
Predicting Multi-Codebook Vector Quantization Indexes for Knowledge Distillation—0
Lightweight Neural Network with Knowledge Distillation for CSI Feedback—0
QuaLA-MiniLM: a Quantized Length Adaptive MiniLM—0
Generative Negative Text Replay for Continual Vision-Language Pretraining—0
Application of Knowledge Distillation to Multi-task Speech Representation Learning—0
Show:102550
← PrevPage 48 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