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 3801–3850 of 4240 papers

TitleStatusHype
Modality-Independent Brain Lesion Segmentation with Privacy-aware Continual LearningCode0
Squeezed Deep 6DoF Object Detection Using Knowledge DistillationCode0
Unsupervised Spike Depth Estimation via Cross-modality Cross-domain Knowledge TransferCode0
Adaptive Modality Balanced Online Knowledge Distillation for Brain-Eye-Computer based Dim Object DetectionCode0
Distilling Influences to Mitigate Prediction Churn in Graph Neural NetworksCode0
Model-Architecture Co-Design for High Performance Temporal GNN Inference on FPGACode0
Closest Neighbors are Harmful for Lightweight Masked Auto-encodersCode0
CLIMB-3D: Continual Learning for Imbalanced 3D Instance SegmentationCode0
RAIN: RegulArization on Input and Network for Black-Box Domain AdaptationCode0
Reprogramming Distillation for Medical Foundation ModelsCode0
Model Compression Techniques in Biometrics Applications: A SurveyCode0
Unsupervised Training of a Dynamic Context-Aware Deep Denoising Framework for Low-Dose Fluoroscopic ImagingCode0
Comb, Prune, Distill: Towards Unified Pruning for Vision Model CompressionCode0
Class Incremental Fault Diagnosis under Limited Fault Data via Supervised Contrastive Knowledge DistillationCode0
StableKD: Breaking Inter-block Optimization Entanglement for Stable Knowledge DistillationCode0
Toward Extremely Lightweight Distracted Driver Recognition With Distillation-Based Neural Architecture Search and Knowledge TransferCode0
Distilling Implicit Multimodal Knowledge into Large Language Models for Zero-Resource Dialogue GenerationCode0
Distilling Image Dehazing With Heterogeneous Task ImitationCode0
Enhancing Heterogeneous Federated Learning with Knowledge Extraction and Multi-Model FusionCode0
Modeling Document-level Temporal Structures for Building Temporal Dependency GraphsCode0
Guiding Frame-Level CTC Alignments Using Self-knowledge DistillationCode0
Data Efficient Stagewise Knowledge DistillationCode0
Weight-Inherited Distillation for Task-Agnostic BERT CompressionCode0
StatsMerging: Statistics-Guided Model Merging via Task-Specific Teacher DistillationCode0
Why Not Transform Chat Large Language Models to Non-English?Code0
Response Ranking with Deep Matching Networks and External Knowledge in Information-seeking Conversation SystemsCode0
Distilling Global and Local Logits With Densely Connected RelationsCode0
UPFL: Unsupervised Personalized Federated Learning towards New ClientsCode0
GSSF: Generalized Structural Sparse Function for Deep Cross-modal Metric LearningCode0
Two-stage Textual Knowledge Distillation for End-to-End Spoken Language UnderstandingCode0
Distilling Focal Knowledge From Imperfect Expert for 3D Object DetectionCode0
Distilling and Transferring Knowledge via cGAN-generated Samples for Image Classification and RegressionCode0
MoMA: Momentum Contrastive Learning with Multi-head Attention-based Knowledge Distillation for Histopathology Image AnalysisCode0
Exploring Inconsistent Knowledge Distillation for Object Detection with Data AugmentationCode0
GSB: Group Superposition Binarization for Vision Transformer with Limited Training SamplesCode0
Distilled Non-Semantic Speech Embeddings with Binary Neural Networks for Low-Resource DevicesCode0
Group Multi-View Transformer for 3D Shape Analysis with Spatial EncodingCode0
Greedy-layer Pruning: Speeding up Transformer Models for Natural Language ProcessingCode0
Automatic Assignment of Radiology Examination Protocols Using Pre-trained Language Models with Knowledge DistillationCode0
Graph Knowledge Distillation to Mixture of ExpertsCode0
Mosaic: Data-Free Knowledge Distillation via Mixture-of-Experts for Heterogeneous Distributed EnvironmentsCode0
Graph Entropy Minimization for Semi-supervised Node ClassificationCode0
Rethinking Intermediate Layers design in Knowledge Distillation for Kidney and Liver Tumor SegmentationCode0
AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture SearchCode0
Graph-based Knowledge Distillation by Multi-head Attention NetworkCode0
Gradient Knowledge Distillation for Pre-trained Language ModelsCode0
MSE-Optimal Neural Network Initialization via Layer FusionCode0
Automatic adaptation of object detectors to new domains using self-trainingCode0
MST-KD: Multiple Specialized Teachers Knowledge Distillation for Fair Face RecognitionCode0
STKDRec: Spatial-Temporal Knowledge Distillation for Takeaway RecommendationCode0
Show:102550
← PrevPage 77 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