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
ESPnet-ST IWSLT 2021 Offline Speech Translation System—0
Local-Global Knowledge Distillation in Heterogeneous Federated Learning with Non-IID Data—0
Reward-Based 1-bit Compressed Federated Distillation on Blockchain—0
Learning without Forgetting for 3D Point Cloud ObjectsCode0
Adapt-and-Distill: Developing Small, Fast and Effective Pretrained Language Models for Domains—0
PQK: Model Compression via Pruning, Quantization, and Knowledge Distillation—0
Dealing with training and test segmentation mismatch: FBK@IWSLT2021—0
Efficient Inference via Universal LSH Kernel—0
Knowledge Distillation via Instance-level Sequence Learning—0
Positive-Unlabeled Data Purification in the Wild for Object Detection—0
Data-Free Knowledge Distillation for Image Super-ResolutionCode0
Space-Time Distillation for Video Super-Resolution—0
Cross Modality Knowledge Distillation for Multi-Modal Aerial View Object ClassificationCode0
Minimally Invasive Surgery for Sparse Neural Networks in Contrastive Manner—0
Teacher's pet: understanding and mitigating biases in distillation—0
Tree-Like Decision Distillation—0
CapsuleRRT: Relationships-Aware Regression Tracking via Capsules—0
Recurrent Stacking of Layers in Neural Networks: An Application to Neural Machine Translation—0
Dual-Teacher Class-Incremental Learning With Data-Free Generative Replay—0
Knowledge distillation from multi-modal to mono-modal segmentation networks—0
Dynamic Knowledge Distillation With Noise Elimination for RGB-D Salient Object Detection—0
Topology Distillation for Recommender System—0
Simon Says: Evaluating and Mitigating Bias in Pruned Neural Networks with Knowledge DistillationCode0
CoDERT: Distilling Encoder Representations with Co-learning for Transducer-based Speech Recognition—0
Energy-efficient Knowledge Distillation for Spiking Neural Networks—0
LENAS: Learning-based Neural Architecture Search and Ensemble for 3D Radiotherapy Dose PredictionCode0
Guiding Teacher Forcing with Seer Forcing for Neural Machine Translation—0
Generate, Annotate, and Learn: NLP with Synthetic TextCode0
RefBERT: Compressing BERT by Referencing to Pre-computed Representations—0
Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge DistillationCode0
AKE-GNN: Effective Graph Learning with Adaptive Knowledge Exchange—0
Learning by Distillation: A Self-Supervised Learning Framework for Optical Flow Estimation—0
RoSearch: Search for Robust Student Architectures When Distilling Pre-trained Language Models—0
MergeDistill: Merging Pre-trained Language Models using Distillation—0
ERNIE-Tiny : A Progressive Distillation Framework for Pretrained Transformer CompressionCode0
Not All Knowledge Is Created Equal: Mutual Distillation of Confident Knowledge—0
Rejuvenating Low-Frequency Words: Making the Most of Parallel Data in Non-Autoregressive TranslationCode0
One Teacher is Enough? Pre-trained Language Model Distillation from Multiple Teachers—0
Cost-effective Deployment of BERT Models in Serverless Environment—0
Modality-specific Distillation—0
Multi-Grained Knowledge Distillation for Named Entity Recognition—0
Natural Statistics of Network Activations and Implications for Knowledge Distillation—0
Reinforced Iterative Knowledge Distillation for Cross-Lingual Named Entity Recognition—0
Continual Learning for Neural Machine Translation—0
Claim Matching Beyond English to Scale Global Fact-Checking—0
Greedy-layer Pruning: Speeding up Transformer Models for Natural Language ProcessingCode0
FReTAL: Generalizing Deepfake Detection using Knowledge Distillation and Representation Learning—0
Not Far Away, Not So Close: Sample Efficient Nearest Neighbour Data Augmentation via MiniMaxCode0
Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation—0
Towards Understanding Knowledge 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