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 2051–2100 of 4240 papers

TitleStatusHype
Knowledge Distillation from Multiple Foundation Models for End-to-End Speech Recognition—0
Efficient Compression of Multitask Multilingual Speech Models—0
Collaborative Learning for Deep Neural Networks—0
Efficient and Robust Knowledge Distillation from A Stronger Teacher Based on Correlation Matching—0
Collaborative Inter-agent Knowledge Distillation for Reinforcement Learning—0
A Survey of Techniques for Optimizing Transformer Inference—0
Adverse Weather Optical Flow: Cumulative Homogeneous-Heterogeneous Adaptation—0
Efficient AI in Practice: Training and Deployment of Efficient LLMs for Industry Applications—0
Collaborative Distillation in the Parameter and Spectrum Domains for Video Action Recognition—0
Efficiency optimization of large-scale language models based on deep learning in natural language processing tasks—0
A Survey of Model Compression and Acceleration for Deep Neural Networks—0
A Bayesian Optimization Framework for Neural Network Compression—0
Effective Training of Convolutional Neural Networks with Low-bitwidth Weights and Activations—0
Collaborative Distillation for Top-N Recommendation—0
Effectiveness of Function Matching in Driving Scene Recognition—0
A Survey of Methods for Low-Power Deep Learning and Computer Vision—0
A Study on the Efficiency and Generalization of Light Hybrid Retrievers—0
Effectiveness of Arbitrary Transfer Sets for Data-free Knowledge Distillation—0
Effective Decision Boundary Learning for Class Incremental Learning—0
EFCM: Efficient Fine-tuning on Compressed Models for deployment of large models in medical image analysis—0
EEGMobile: Enhancing Speed and Accuracy in EEG-Based Gaze Prediction with Advanced Mobile Architectures—0
Cold & Warm Net: Addressing Cold-Start Users in Recommender Systems—0
Active Data Curation Effectively Distills Large-Scale Multimodal Models—0
Knowledge Distillation from Few Samples—0
Knowledge Distillation from Non-streaming to Streaming ASR Encoder using Auxiliary Non-streaming Layer—0
Knowledge Distillation Neural Network for Predicting Car-following Behaviour of Human-driven and Autonomous Vehicles—0
Knowledge Distillation via Weighted Ensemble of Teaching Assistants—0
LAMeTA: Intent-Aware Agentic Network Optimization via a Large AI Model-Empowered Two-Stage Approach—0
EduPal leaves no professor behind: Supporting faculty via a peer-powered recommender system—0
A Study on Knowledge Distillation from Weak Teacher for Scaling Up Pre-trained Language Models—0
Education distillation:getting student models to learn in shcools—0
EDocNet: Efficient Datasheet Layout Analysis Based on Focus and Global Knowledge Distillation—0
CoDERT: Distilling Encoder Representations with Co-learning for Transducer-based Speech Recognition—0
Active Class Incremental Learning for Imbalanced Datasets—0
EdgeFusion: On-Device Text-to-Image Generation—0
CoCo DistillNet: a Cross-layer Correlation Distillation Network for Pathological Gastric Cancer Segmentation—0
Edge-free but Structure-aware: Prototype-Guided Knowledge Distillation from GNNs to MLPs—0
EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation—0
A Study of Non-autoregressive Model for Sequence Generation—0
Knowledge Distillation for Underwater Feature Extraction and Matching via GAN-synthesized Images—0
Edge-Efficient Deep Learning Models for Automatic Modulation Classification: A Performance Analysis—0
Edge AI-Enabled Chicken Health Detection Based on Enhanced FCOS-Lite and Knowledge Distillation—0
EchoLM: Accelerating LLM Serving with Real-time Knowledge Distillation—0
CMU’s IWSLT 2022 Dialect Speech Translation System—0
Adversarial Sparse Teacher: Defense Against Distillation-Based Model Stealing Attacks Using Adversarial Examples—0
EchoAtt: Attend, Copy, then Adjust for More Efficient Large Language Models—0
ECG-guided individual identification via PPG—0
ECAT: A Entire space Continual and Adaptive Transfer Learning Framework for Cross-Domain Recommendation—0
Asterisk*: Keep it Simple—0
A baseline revisited: Pushing the limits of multi-segment models for context-aware translation—0
Show:102550
← PrevPage 42 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