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 3251–3300 of 4240 papers

TitleStatusHype
MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation—0
CL-ReKD: Cross-lingual Knowledge Distillation for Multilingual Retrieval Question Answering—0
Nearest Neighbor Knowledge Distillation for Neural Machine Translation—0
Transferring Knowledge from Structure-aware Self-attention Language Model to Sequence-to-Sequence Semantic Parsing—0
Tree Knowledge Distillation for Compressing Transformer-Based Language Models—0
Technical Report for ICCV 2021 Challenge SSLAD-Track3B: Transformers Are Better Continual Learners—0
On Exploring Pose Estimation as an Auxiliary Learning Task for Visible-Infrared Person Re-identificationCode0
FedDTG:Federated Data-Free Knowledge Distillation via Three-Player Generative Adversarial Networks—0
Two-Pass End-to-End ASR Model Compression—0
Microdosing: Knowledge Distillation for GAN based Compression—0
Class-Incremental Continual Learning into the eXtended DER-verse—0
Which Student is Best? A Comprehensive Knowledge Distillation Exam for Task-Specific BERT Models—0
Improving Video Model Transfer With Dynamic Representation Learning—0
Distillation Using Oracle Queries for Transformer-Based Human-Object Interaction Detection—0
Class Similarity Weighted Knowledge Distillation for Continual Semantic Segmentation—0
Image Restoration using Feature-guidance—0
Performance-Aware Mutual Knowledge Distillation for Improving Neural Architecture Search—0
Multi-Objective Diverse Human Motion Prediction With Knowledge Distillation—0
Conditional Generative Data-free Knowledge Distillation—0
Data-Free Knowledge Transfer: A Survey—0
An Efficient Federated Distillation Learning System for Multi-task Time Series Classification—0
Automatic Mixed-Precision Quantization Search of BERT—0
Online Adversarial Knowledge Distillation for Graph Neural NetworksCode0
Distilling the Knowledge of Romanian BERTs Using Multiple TeachersCode0
Adaptive Beam Search to Enhance On-device Abstractive Summarization—0
Self-Distillation Mixup Training for Non-autoregressive Neural Machine Translation—0
Supervised Graph Contrastive Pretraining for Text Classification—0
Multi-Modality Distillation via Learning the teacher's modality-level Gram Matrix—0
Controlling the Quality of Distillation in Response-Based Network Compression—0
LegoDNN: Block-grained Scaling of Deep Neural Networks for Mobile Vision—0
Weakly Supervised Semantic Segmentation via Alternative Self-Dual Teaching—0
Distillation of Human-Object Interaction Contexts for Action Recognition—0
Knowledge Distillation Improves Stability in Retranslation-based Simultaneous Translation—0
Towards Disturbance-Free Visual Mobile ManipulationCode0
Distill and De-bias: Mitigating Bias in Face Verification using Knowledge Distillation—0
Amortized Noisy Channel Neural Machine Translation—0
Towards a Unified Foundation Model: Jointly Pre-Training Transformers on Unpaired Images and Text—0
On the Use of External Data for Spoken Named Entity RecognitionCode0
Improving Sequential Recommendations via Bidirectional Temporal Data Augmentation with Pre-trainingCode0
Lifelong Unsupervised Domain Adaptive Person Re-identification with Coordinated Anti-forgetting and Adaptation—0
Human Guided Exploitation of Interpretable Attention Patterns in Summarization and Topic SegmentationCode0
Mutual Adversarial Training: Learning together is better than going alone—0
Knowledge Distillation for Object Detection via Rank Mimicking and Prediction-guided Feature Imitation—0
Boosting Contrastive Learning with Relation Knowledge Distillation—0
ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake ImagesCode0
Auxiliary Learning for Self-Supervised Video Representation via Similarity-based Knowledge DistillationCode0
CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks—0
Safe Distillation Box—0
Extracting knowledge from features with multilevel abstraction—0
KDCTime: Knowledge Distillation with Calibration on InceptionTime for Time-series Classification—0
Show:102550
← PrevPage 66 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