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 4001–4050 of 4240 papers

TitleStatusHype
Understanding Knowledge Distillation in Non-autoregressive Machine Translation—0
Data Diversification: A Simple Strategy For Neural Machine TranslationCode1
ESPnet How2 Speech Translation System for IWSLT 2019: Pre-training, Knowledge Distillation, and Going Deeper—0
Weakly Supervised Cross-lingual Semantic Relation Classification via Knowledge Distillation—0
Natural Language Generation for Effective Knowledge DistillationCode0
Distilling Pixel-Wise Feature Similarities for Semantic Segmentation—0
A Simple but Effective BERT Model for Dialog State Tracking on Resource-Limited Systems—0
MOD: A Deep Mixture Model with Online Knowledge Distillation for Large Scale Video Temporal Concept LocalizationCode0
Variational Student: Learning Compact and Sparser Networks in Knowledge Distillation Framework—0
Secost: Sequential co-supervision for large scale weakly labeled audio event detection—0
An Empirical Study of Efficient ASR Rescoring with Transformers—0
Adversarial Feature Alignment: Avoid Catastrophic Forgetting in Incremental Task Lifelong Learning—0
Contrastive Representation DistillationCode1
Model Compression with Two-stage Multi-teacher Knowledge Distillation for Web Question Answering System—0
A Generalized and Robust Method Towards Practical Gaze Estimation on Smart Phone—0
Noise as a Resource for Learning in Knowledge Distillation—0
VarGFaceNet: An Efficient Variable Group Convolutional Neural Network for Lightweight Face RecognitionCode0
Cross-modal knowledge distillation for action recognition—0
FedMD: Heterogenous Federated Learning via Model DistillationCode1
Knowledge Distillation from Internal Representations—0
Distilling BERT into Simple Neural Networks with Unlabeled Transfer Data—0
On the Efficacy of Knowledge Distillation—0
Improving Word Embedding Factorization for Compression Using Distilled Nonlinear Neural Decomposition—0
AntMan: Sparse Low-Rank Compression to Accelerate RNN inference—0
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighterCode1
Distilled Split Deep Neural Networks for Edge-Assisted Real-Time SystemsCode1
A Bayesian Optimization Framework for Neural Network Compression—0
Distillation-Based Training for Multi-Exit ArchitecturesCode1
Training convolutional neural networks with cheap convolutions and online distillationCode0
Compact Trilinear Interaction for Visual Question AnsweringCode0
Distilled embedding: non-linear embedding factorization using knowledge distillation—0
Collaborative Inter-agent Knowledge Distillation for Reinforcement Learning—0
Proactive Sequence Generator via Knowledge Acquisition—0
XD: Cross-lingual Knowledge Distillation for Polyglot Sentence Embeddings—0
SELF-KNOWLEDGE DISTILLATION ADVERSARIAL ATTACK—0
Revisiting Knowledge Distillation via Label Smoothing RegularizationCode0
Extremely Small BERT Models from Mixed-Vocabulary Training—0
Technical report on Conversational Question Answering—0
FEED: Feature-level Ensemble for Knowledge Distillation—0
TinyBERT: Distilling BERT for Natural Language UnderstandingCode0
Positive-Unlabeled Compression on the CloudCode2
Learning Lightweight Pedestrian Detector with Hierarchical Knowledge Distillation—0
Ensemble Knowledge Distillation for Learning Improved and Efficient NetworksCode0
Knowledge Transfer Graph for Deep Collaborative LearningCode0
Accelerating Transformer Decoding via a Hybrid of Self-attention and Recurrent Neural Network—0
Knowledge distillation for optimization of quantized deep neural networks—0
Knowledge Distillation for End-to-End Person SearchCode0
Online Sensor Hallucination via Knowledge Distillation for Multimodal Image Classification—0
Patient Knowledge Distillation for BERT Model CompressionCode0
Well-Read Students Learn Better: On the Importance of Pre-training Compact ModelsCode2
Show:102550
← PrevPage 81 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