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 3201–3250 of 4240 papers

TitleStatusHype
Segmentation with mixed supervision: Confidence maximization helps knowledge distillationCode1
RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation—0
Knowledge Distillation with Noisy Labels for Natural Language Understanding—0
Releasing Graph Neural Networks with Differential Privacy GuaranteesCode0
Towards Full Utilization on Mask Task for Distilling PLMs into NMT—0
Distilling Linguistic Context for Language Model CompressionCode1
Label Assignment Distillation for Object Detection—0
The NiuTrans System for WNGT 2020 Efficiency TaskCode1
The NiuTrans System for the WMT21 Efficiency TaskCode1
New Perspective on Progressive GANs Distillation for One-class Novelty Detection—0
EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge DistillationCode1
Secure Your Ride: Real-time Matching Success Rate Prediction for Passenger-Driver Pairs—0
Multi-Scale Aligned Distillation for Low-Resolution DetectionCode1
Multihop: Leveraging Complex Models to Learn Accurate Simple Models—0
A Note on Knowledge Distillation Loss Function for Object Classification—0
AligNART: Non-autoregressive Neural Machine Translation by Jointly Learning to Estimate Alignment and Translate—0
UniMS: A Unified Framework for Multimodal Summarization with Knowledge Distillation—0
How to Select One Among All? An Extensive Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language UnderstandingCode1
KroneckerBERT: Learning Kronecker Decomposition for Pre-trained Language Models via Knowledge Distillation—0
On the Efficiency of Subclass Knowledge Distillation in Classification Tasks—0
Federated Ensemble Model-based Reinforcement Learning in Edge Computing—0
Learning to Teach with Student Feedback—0
Towards Developing a Multilingual and Code-Mixed Visual Question Answering System by Knowledge Distillation—0
LibFewShot: A Comprehensive Library for Few-shot LearningCode2
Dual Correction Strategy for Ranking Distillation in Top-N Recommender SystemCode0
Knowledge Distillation Using Hierarchical Self-Supervision Augmented DistributionCode1
Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT CompressionCode1
Complementary Calibration: Boosting General Continual Learning with Collaborative Distillation and Self-SupervisionCode0
CAM-loss: Towards Learning Spatially Discriminative Feature Representations—0
Knowledge Distillation with BERT for Image Tag-Based Privacy Prediction—0
Decoupled Transformer for Scalable Inference in Open-domain Question Answering—0
Black-Box Attacks on Sequential Recommenders via Data-Free Model ExtractionCode1
Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge DistillationCode0
FedKD: Communication Efficient Federated Learning via Knowledge Distillation—0
Lipschitz Continuity Guided Knowledge Distillation—0
Distilling the Knowledge of Large-scale Generative Models into Retrieval Models for Efficient Open-domain ConversationCode0
SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation—0
CoCo DistillNet: a Cross-layer Correlation Distillation Network for Pathological Gastric Cancer Segmentation—0
Efficient training of lightweight neural networks using Online Self-Acquired Knowledge Distillation—0
Cross-category Video Highlight Detection via Set-based LearningCode1
PocketNet: Extreme Lightweight Face Recognition Network using Neural Architecture Search and Multi-Step Knowledge DistillationCode1
Deploying a BERT-based Query-Title Relevance Classifier in a Production System: a View from the Trenches—0
Efficient Medical Image Segmentation Based on Knowledge DistillationCode1
Personalised Federated Learning: A Combinational Approach—0
Supervised Compression for Resource-Constrained Edge Computing SystemsCode1
Boosting of Head Pose Estimation by Knowledge Distillation—0
Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student BetterCode1
Learning Conditional Knowledge Distillation for Degraded-Reference Image Quality AssessmentCode1
BERT Learns to Teach: Knowledge Distillation with Meta Learning—0
G-DetKD: Towards General Distillation Framework for Object Detectors via Contrastive and Semantic-guided Feature Imitation—0
Show:102550
← PrevPage 65 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