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 3801–3850 of 4240 papers

TitleStatusHype
Unsupervised Multi-Target Domain Adaptation Through Knowledge DistillationCode1
Knowledge Distillation for Multi-task LearningCode1
Learning to Learn Parameterized Classification Networks for Scalable Input ImagesCode1
Towards Practical Lipreading with Distilled and Efficient ModelsCode1
RATT: Recurrent Attention to Transient Tasks for Continual Image CaptioningCode1
Representation Transfer by Optimal Transport—0
Dual-Teacher: Integrating Intra-domain and Inter-domain Teachers for Annotation-efficient Cardiac Segmentation—0
Temporal Self-Ensembling Teacher for Semi-Supervised Object DetectionCode1
Optical Flow Distillation: Towards Efficient and Stable Video Style Transfer—0
Data-Efficient Ranking Distillation for Image Retrieval—0
Robust Re-Identification by Multiple Views Knowledge DistillationCode1
Tracking-by-Trackers with a Distilled and Reinforced ModelCode1
Improving Weakly Supervised Visual Grounding by Contrastive Knowledge DistillationCode1
Knowledge Distillation Beyond Model Compression—0
Interactive Knowledge Distillation—0
Improving Autoregressive NMT with Non-Autoregressive Model—0
Xiaomi's Submissions for IWSLT 2020 Open Domain Translation Task—0
CASIA's System for IWSLT 2020 Open Domain Translation—0
Exploring the Limits of Simple Learners in Knowledge Distillation for Document Classification with DocBERT—0
SimulSpeech: End-to-End Simultaneous Speech to Text Translation—0
Improving Event Detection via Open-domain Trigger KnowledgeCode1
On the Demystification of Knowledge Distillation: A Residual Network Perspective—0
Extracurricular Learning: Knowledge Transfer Beyond Empirical Distribution—0
Interpreting and Disentangling Feature Components of Various Complexity from DNNsCode0
Motion Pyramid Networks for Accurate and Efficient Cardiac Motion Estimation—0
Diverse Knowledge Distillation (DKD): A Solution for Improving The Robustness of Ensemble Models Against Adversarial Attacks—0
Streaming Transformer ASR with Blockwise Synchronous Inference—0
Distilling Object Detectors with Task Adaptive Regularization—0
Self-Knowledge Distillation with Progressive Refinement of TargetsCode1
Paying more attention to snapshots of Iterative Pruning: Improving Model Compression via Ensemble DistillationCode1
Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine TranslationCode1
Self-supervised Knowledge Distillation for Few-shot LearningCode1
Prior knowledge distillation based on financial time series—0
Multi-fidelity Neural Architecture Search with Knowledge DistillationCode0
AutoGAN-Distiller: Searching to Compress Generative Adversarial NetworksCode1
Pixel Invisibility: Detecting Objects Invisible in Color Images—0
Knowledge Distillation Meets Self-SupervisionCode1
Ensemble Distillation for Robust Model Fusion in Federated LearningCode0
Real-Time Video Inference on Edge Devices via Adaptive Model StreamingCode1
Adjoined Networks: A Training Paradigm with Applications to Network CompressionCode1
Knowledge Distillation: A Survey—0
Continual Representation Learning for Biometric IdentificationCode0
Classification Under Misspecification: Halfspaces, Generalized Linear Models, and Connections to EvolvabilityCode0
FastSpeech 2: Fast and High-Quality End-to-End Text to SpeechCode1
ResKD: Residual-Guided Knowledge Distillation—0
Multi-view Contrastive Learning for Online Knowledge DistillationCode1
ADMP: An Adversarial Double Masks Based Pruning Framework For Unsupervised Cross-Domain Compression—0
Peer Collaborative Learning for Online Knowledge DistillationCode1
An Empirical Analysis of the Impact of Data Augmentation on Knowledge Distillation—0
An Overview of Neural Network Compression—0
Show:102550
← PrevPage 77 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