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 1051–1100 of 4240 papers

TitleStatusHype
Learning Lightweight Lane Detection CNNs by Self Attention DistillationCode0
Leveraging knowledge distillation for partial multi-task learning from multiple remote sensing datasetsCode0
MST-KD: Multiple Specialized Teachers Knowledge Distillation for Fair Face RecognitionCode0
Leaning Compact and Representative Features for Cross-Modality Person Re-IdentificationCode0
Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self DistillationCode0
Dealing With Heterogeneous 3D MR Knee Images: A Federated Few-Shot Learning Method With Dual Knowledge DistillationCode0
Language-Universal Adapter Learning with Knowledge Distillation for End-to-End Multilingual Speech RecognitionCode0
Large-Scale Data-Free Knowledge Distillation for ImageNet via Multi-Resolution Data GenerationCode0
Beyond the Limitation of Monocular 3D Detector via Knowledge DistillationCode0
DCA: Dividing and Conquering Amnesia in Incremental Object DetectionCode0
Data Upcycling Knowledge Distillation for Image Super-ResolutionCode0
Dataset Distillation via Knowledge Distillation: Towards Efficient Self-Supervised Pre-Training of Deep NetworksCode0
KS-DETR: Knowledge Sharing in Attention Learning for Detection TransformerCode0
Language Model Knowledge Distillation for Efficient Question Answering in SpanishCode0
KnowledgeSG: Privacy-Preserving Synthetic Text Generation with Knowledge Distillation from ServerCode0
Adaptive Mixing of Auxiliary Losses in Supervised LearningCode0
Data-Free Knowledge Distillation for Image Super-ResolutionCode0
Data-free Knowledge Distillation for Fine-grained Visual CategorizationCode0
Beyond Conventional Transformers: The Medical X-ray Attention (MXA) Block for Improved Multi-Label Diagnosis Using Knowledge DistillationCode0
Knowledge Extraction with No Observable DataCode0
Knowledge Grafting of Large Language ModelsCode0
Knowledge Transfer Graph for Deep Collaborative LearningCode0
Data-free Knowledge Distillation for Segmentation using Data-Enriching GANCode0
Data-Free Generative Replay for Class-Incremental Learning on Imbalanced DataCode0
Knowledge Distillation with Adversarial Samples Supporting Decision BoundaryCode0
Knowledge Distillation with Reptile Meta-Learning for Pretrained Language Model CompressionCode0
Knowledge Distillation via Instance Relationship GraphCode0
Data-Free Adversarial DistillationCode0
Data exploitation: multi-task learning of object detection and semantic segmentation on partially annotated dataCode0
Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge DistillationCode0
Better Supervisory Signals by Observing Learning PathsCode0
Align-to-Distill: Trainable Attention Alignment for Knowledge Distillation in Neural Machine TranslationCode0
Knowledge Distillation of Russian Language Models with Reduction of VocabularyCode0
Knowledge Distillation Layer that Lets the Student DecideCode0
Knowledge Distillation Performs Partial Variance ReductionCode0
DASK: Distribution Rehearsing via Adaptive Style Kernel Learning for Exemplar-Free Lifelong Person Re-IdentificationCode0
Knowledge Distillation from Single to Multi Labels: an Empirical StudyCode0
Knowledge Distillation from Cross Teaching Teachers for Efficient Semi-Supervised Abdominal Organ Segmentation in CTCode0
Few Sample Knowledge Distillation for Efficient Network CompressionCode0
Knowledge Distillation in RNN-Attention Models for Early Prediction of Student PerformanceCode0
DAD++: Improved Data-free Test Time Adversarial DefenseCode0
DAdEE: Unsupervised Domain Adaptation in Early Exit PLMsCode0
BEiT v2: Masked Image Modeling with Vector-Quantized Visual TokenizersCode0
Being Strong Progressively! Enhancing Knowledge Distillation of Large Language Models through a Curriculum Learning FrameworkCode0
Knowledge Distillation for Quality EstimationCode0
Knowledge Distillation for Singing Voice DetectionCode0
Aligning (Medical) LLMs for (Counterfactual) FairnessCode0
D^2TV: Dual Knowledge Distillation and Target-oriented Vision Modeling for Many-to-Many Multimodal SummarizationCode0
cViL: Cross-Lingual Training of Vision-Language Models using Knowledge DistillationCode0
BEBERT: Efficient and Robust Binary Ensemble BERTCode0
Show:102550
← PrevPage 22 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