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
Scaling Sparse and Dense Retrieval in Decoder-Only LLMsCode1
Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation?Code1
DA-Mamba: Domain Adaptive Hybrid Mamba-Transformer Based One-Stage Object DetectionCode1
Enhancing Cross-Tokenizer Knowledge Distillation with Contextual Dynamical MappingCode1
Audio-Visual Representation Learning via Knowledge Distillation from Speech Foundation ModelsCode1
Towards Unified Music Emotion Recognition across Dimensional and Categorical ModelsCode1
Return of the Encoder: Maximizing Parameter Efficiency for SLMsCode1
Towards Fast, Specialized Machine Learning Force Fields: Distilling Foundation Models via Energy HessiansCode1
Efficient Traffic Prediction Through Spatio-Temporal DistillationCode1
From My View to Yours: Ego-Augmented Learning in Large Vision Language Models for Understanding Exocentric Daily Living ActivitiesCode1
ConcealGS: Concealing Invisible Copyright Information in 3D Gaussian SplattingCode1
V2X-DGPE: Addressing Domain Gaps and Pose Errors for Robust Collaborative 3D Object DetectionCode1
Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Large Model EnhancementCode1
LiRCDepth: Lightweight Radar-Camera Depth Estimation via Knowledge Distillation and Uncertainty GuidanceCode1
Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion ModelsCode1
Multi-Level Optimal Transport for Universal Cross-Tokenizer Knowledge Distillation on Language ModelsCode1
Relation-Guided Adversarial Learning for Data-free Knowledge TransferCode1
Dynamic Contrastive Knowledge Distillation for Efficient Image RestorationCode1
Unlocking the Potential of Reverse Distillation for Anomaly DetectionCode1
Cloud Object Detector Adaptation by Integrating Different Source KnowledgeCode1
One-shot Federated Learning via Synthetic Distiller-Distillate CommunicationCode1
Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language ModelCode1
Vision Mamba Distillation for Low-resolution Fine-grained Image ClassificationCode1
Learn from Foundation Model: Fruit Detection Model without Manual AnnotationCode1
LLM-Neo: Parameter Efficient Knowledge Distillation for Large Language ModelsCode1
Towards Competitive Search Relevance For Inference-Free Learned Sparse RetrieversCode1
KD-LoRA: A Hybrid Approach to Efficient Fine-Tuning with LoRA and Knowledge DistillationCode1
TransAgent: Transfer Vision-Language Foundation Models with Heterogeneous Agent CollaborationCode1
Breaking Modality Gap in RGBT Tracking: Coupled Knowledge DistillationCode1
Mentor-KD: Making Small Language Models Better Multi-step ReasonersCode1
PairDistill: Pairwise Relevance Distillation for Dense RetrievalCode1
HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard ModelsCode1
Domain Consistency Representation Learning for Lifelong Person Re-IdentificationCode1
AIM 2024 Challenge on UHD Blind Photo Quality AssessmentCode1
Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning TasksCode1
Effective Pre-Training of Audio Transformers for Sound Event DetectionCode1
EchoDFKD: Data-Free Knowledge Distillation for Cardiac Ultrasound Segmentation using Synthetic DataCode1
EasyST: A Simple Framework for Spatio-Temporal PredictionCode1
LEROjD: Lidar Extended Radar-Only Object DetectionCode1
DKDM: Data-Free Knowledge Distillation for Diffusion Models with Any ArchitectureCode1
Designing Large Foundation Models for Efficient Training and Inference: A SurveyCode1
MobileIQA: Exploiting Mobile-level Diverse Opinion Network For No-Reference Image Quality Assessment Using Knowledge DistillationCode1
Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual LearningCode1
GenFormer -- Generated Images are All You Need to Improve Robustness of Transformers on Small DatasetsCode1
Knowledge Distillation with Refined LogitsCode1
One Step Diffusion-based Super-Resolution with Time-Aware DistillationCode1
Real-time Event Recognition of Long-distance Distributed Vibration Sensing with Knowledge Distillation and Hardware AccelerationCode1
Unsupervised Domain Adaption Harnessing Vision-Language Pre-trainingCode1
Pruning Large Language Models with Semi-Structural Adaptive Sparse TrainingCode1
Modality-Balanced Learning for Multimedia RecommendationCode1
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