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

Showing 27512800 of 4240 papers

TitleStatusHype
CMU’s IWSLT 2022 Dialect Speech Translation System0
Model Distillation for Faithful Explanations of Medical Code Predictions0
An Unsupervised Multiple-Task and Multiple-Teacher Model for Cross-lingual Named Entity Recognition0
Multi-Granularity Structural Knowledge Distillation for Language Model CompressionCode0
The Xiaomi Text-to-Text Simultaneous Speech Translation System for IWSLT 20220
Domain Knowledge Transferring for Pre-trained Language Model via Calibrated Activation Boundary DistillationCode0
Domain-specific knowledge distillation yields smaller and better models for conversational commerce0
Pretrained Speech Encoders and Efficient Fine-tuning Methods for Speech Translation: UPC at IWSLT 2022Code0
Low Resource Causal Event Detection from Biomedical Literature0
Nearest Neighbor Knowledge Distillation for Neural Machine TranslationCode1
EasyNLP: A Comprehensive and Easy-to-use Toolkit for Natural Language Processing0
Multiple Degradation and Reconstruction Network for Single Image Denoising via Knowledge Distillation0
Curriculum Learning for Dense Retrieval DistillationCode1
DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers0
Human-Centered Prior-Guided and Task-Dependent Multi-Task Representation Learning for Action Recognition Pre-Training0
Conformer and Blind Noisy Students for Improved Image Quality AssessmentCode1
Transfer Learning with Pre-trained Conditional Generative Models0
One-shot Federated Learning without Server-side TrainingCode0
Improving Feature Generalizability with Multitask Learning in Class Incremental Learning0
Revisiting Graph based Social Recommendation: A Distillation Enhanced Social Graph Network0
Boosting Pruned Networks with Linear Over-parameterization0
Proto2Proto: Can you recognize the car, the way I do?Code1
Selective Cross-Task Distillation0
Joint Feature Distribution Alignment Learning for NIR-VIS and VIS-VIS Face Recognition0
On-Device Next-Item Recommendation with Self-Supervised Knowledge DistillationCode1
Learning to Purification for Unsupervised Person Re-identification0
Eliminating Backdoor Triggers for Deep Neural Networks Using Attention Relation Graph DistillationCode1
Unseen Object Instance Segmentation with Fully Test-time RGB-D Embeddings Adaptation0
HRPose: Real-Time High-Resolution 6D Pose Estimation Network Using Knowledge Distillation0
DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue GenerationCode1
Modeling Missing Annotations for Incremental Learning in Object DetectionCode1
Multi-Modal Few-Shot Object Detection with Meta-Learning-Based Cross-Modal Prompting0
MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided AdaptationCode1
CILDA: Contrastive Data Augmentation using Intermediate Layer Knowledge Distillation0
Ensemble diverse hypotheses and knowledge distillation for unsupervised cross-subject adaptationCode0
Cross-Image Relational Knowledge Distillation for Semantic SegmentationCode2
Spatial Likelihood Voting with Self-Knowledge Distillation for Weakly Supervised Object Detection0
Impossible Triangle: What's Next for Pre-trained Language Models?0
Localization Distillation for Object DetectionCode2
DistPro: Searching A Fast Knowledge Distillation Process via Meta Optimization0
CoupleFace: Relation Matters for Face Recognition Distillation0
LRH-Net: A Multi-Level Knowledge Distillation Approach for Low-Resource Heart NetworkCode1
Solving ImageNet: a Unified Scheme for Training any Backbone to Top ResultsCode2
Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response DistillationCode1
Towards On-Board Panoptic Segmentation of Multispectral Satellite Images0
Using Explainable Boosting Machine to Compare Idiographic and Nomothetic Approaches for Ecological Momentary Assessment Data0
Co-Teaching for Unsupervised Domain Adaptation and ExpansionCode0
CDKT-FL: Cross-Device Knowledge Transfer using Proxy Dataset in Federated Learning0
DST: Dynamic Substitute Training for Data-free Black-box Attack0
CL-XABSA: Contrastive Learning for Cross-lingual Aspect-based Sentiment AnalysisCode0
Show:102550
← PrevPage 56 of 85Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ScaleKD (T:BEiT-L S:ViT-B/14)Top-1 accuracy %86.43Unverified
2ScaleKD (T:Swin-L S:ViT-B/16)Top-1 accuracy %85.53Unverified
3ScaleKD (T:Swin-L S:ViT-S/16)Top-1 accuracy %83.93Unverified
4ScaleKD (T:Swin-L S:Swin-T)Top-1 accuracy %83.8Unverified
5KD++(T: regnety-16GF S:ViT-B)Top-1 accuracy %83.6Unverified
6VkD (T:RegNety 160 S:DeiT-S)Top-1 accuracy %82.9Unverified
7SpectralKD (T:Swin-S S:Swin-T)Top-1 accuracy %82.7Unverified
8ScaleKD (T:Swin-L S:ResNet-50)Top-1 accuracy %82.55Unverified
9DiffKD (T:Swin-L S: Swin-T)Top-1 accuracy %82.5Unverified
10DIST (T: Swin-L S: Swin-T)Top-1 accuracy %82.3Unverified
#ModelMetricClaimedVerifiedStatus
1SRD (T:resnet-32x4, S:shufflenet-v2)Top-1 Accuracy (%)79.86Unverified
2shufflenet-v2(T:resnet-32x4, S:shufflenet-v2)Top-1 Accuracy (%)78.76Unverified
3MV-MR (T: CLIP/ViT-B-16 S: resnet50)Top-1 Accuracy (%)78.6Unverified
4resnet8x4 (T: resnet32x4 S: resnet8x4)Top-1 Accuracy (%)78.28Unverified
5resnet8x4 (T: resnet32x4 S: resnet8x4 [modified])Top-1 Accuracy (%)78.08Unverified
6ReviewKD++(T:resnet-32x4, S:shufflenet-v2)Top-1 Accuracy (%)77.93Unverified
7ReviewKD++(T:resnet-32x4, S:shufflenet-v1)Top-1 Accuracy (%)77.68Unverified
8resnet8x4 (T: resnet32x4 S: resnet8x4)Top-1 Accuracy (%)77.5Unverified
9resnet8x4 (T: resnet32x4 S: resnet8x4)Top-1 Accuracy (%)76.68Unverified
10resnet8x4 (T: resnet32x4 S: resnet8x4)Top-1 Accuracy (%)76.31Unverified
#ModelMetricClaimedVerifiedStatus
1LSHFM (T: ResNet101 S: ResNet50)mAP93.17Unverified
2LSHFM (T: ResNet101 S: MobileNetV2)mAP90.14Unverified
#ModelMetricClaimedVerifiedStatus
1TIE-KD (T: Adabins S: MobileNetV2)RMSE2.43Unverified