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 151–200 of 4240 papers

TitleStatusHype
Adaptive Multi-Teacher Knowledge Distillation with Meta-LearningCode1
Cross-Modal Fusion Distillation for Fine-Grained Sketch-Based Image RetrievalCode1
Cross-modality Data Augmentation for End-to-End Sign Language TranslationCode1
Block-Wisely Supervised Neural Architecture Search With Knowledge DistillationCode1
Black-box Few-shot Knowledge DistillationCode1
Boosting Multi-Label Image Classification with Complementary Parallel Self-DistillationCode1
Cross-Modality Knowledge Distillation Network for Monocular 3D Object DetectionCode1
Curriculum Learning for Dense Retrieval DistillationCode1
Data-Free Class-Incremental Hand Gesture RecognitionCode1
Hybrid Inverted Index Is a Robust Accelerator for Dense RetrievalCode1
Bit-mask Robust Contrastive Knowledge Distillation for Unsupervised Semantic HashingCode1
BiLD: Bi-directional Logits Difference Loss for Large Language Model DistillationCode1
Cross-Layer Distillation with Semantic CalibrationCode1
BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge DistillationCode1
Bidirectional Distillation for Top-K Recommender SystemCode1
Beyond Self-Supervision: A Simple Yet Effective Network Distillation Alternative to Improve BackbonesCode1
Bi-directional Weakly Supervised Knowledge Distillation for Whole Slide Image ClassificationCode1
BKDSNN: Enhancing the Performance of Learning-based Spiking Neural Networks Training with Blurred Knowledge DistillationCode1
CrossKD: Cross-Head Knowledge Distillation for Object DetectionCode1
Cross-Level Distillation and Feature Denoising for Cross-Domain Few-Shot ClassificationCode1
Beyond Generic: Enhancing Image Captioning with Real-World Knowledge using Vision-Language Pre-Training ModelCode1
Contrastive Representation DistillationCode1
BEV-LGKD: A Unified LiDAR-Guided Knowledge Distillation Framework for BEV 3D Object DetectionCode1
BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object DetectionCode1
SimDistill: Simulated Multi-modal Distillation for BEV 3D Object DetectionCode1
Creating Something from Nothing: Unsupervised Knowledge Distillation for Cross-Modal HashingCode1
Contrastive Deep SupervisionCode1
Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse DataCode1
Contrastive Distillation on Intermediate Representations for Language Model CompressionCode1
Continual evaluation for lifelong learning: Identifying the stability gapCode1
BearingPGA-Net: A Lightweight and Deployable Bearing Fault Diagnosis Network via Decoupled Knowledge Distillation and FPGA AccelerationCode1
Continual Learning for Image Segmentation with Dynamic QueryCode1
Contrastive Model Inversion for Data-Free Knowledge DistillationCode1
Cross-category Video Highlight Detection via Set-based LearningCode1
CrossMatch: Enhance Semi-Supervised Medical Image Segmentation with Perturbation Strategies and Knowledge DistillationCode1
Data-Free Knowledge Distillation for Heterogeneous Federated LearningCode1
Baby Llama: knowledge distillation from an ensemble of teachers trained on a small dataset with no performance penaltyCode1
Designing Large Foundation Models for Efficient Training and Inference: A SurveyCode1
AIM 2024 Challenge on UHD Blind Photo Quality AssessmentCode1
Avatar Knowledge Distillation: Self-ensemble Teacher Paradigm with UncertaintyCode1
AdaptGuard: Defending Against Universal Attacks for Model AdaptationCode1
Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual InformationCode1
Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT CompressionCode1
Black-Box Attacks on Sequential Recommenders via Data-Free Model ExtractionCode1
CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models CascadeCode1
A Knowledge Distillation Framework For Enhancing Ear-EEG Based Sleep Staging With Scalp-EEG DataCode1
Better Estimation of the KL Divergence Between Language ModelsCode1
BERT-of-Theseus: Compressing BERT by Progressive Module ReplacingCode1
Adjoined Networks: A Training Paradigm with Applications to Network CompressionCode1
Backdoor Attacks on Self-Supervised LearningCode1
Show:102550
← PrevPage 4 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