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 401–450 of 4240 papers

TitleStatusHype
A Diversity-Enhanced Knowledge Distillation Model for Practical Math Word Problem SolvingCode0
A Diffusion Model and Knowledge Distillation Framework for Robust Coral Detection in Complex Underwater EnvironmentsCode0
Comprehensive Pathological Image Segmentation via Teacher Aggregation for Tumor Microenvironment Analysis—0
Knowledge Distillation with Adapted Weight—0
LightGNN: Simple Graph Neural Network for RecommendationCode2
Strategic Fusion Optimizes Transformer Compression—0
Optimizing Edge AI: A Comprehensive Survey on Data, Model, and System StrategiesCode2
Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison—0
V2X-DGPE: Addressing Domain Gaps and Pose Errors for Robust Collaborative 3D Object DetectionCode1
Distillation-Enhanced Physical Adversarial Attacks—0
MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders—0
DiagrammaticLearning: A Graphical Language for Compositional Training Regimes—0
Simplification Is All You Need against Out-of-Distribution Overconfidence—0
Tripartite Weight-Space Ensemble for Few-Shot Class-Incremental Learning—0
Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Large Model EnhancementCode1
VL2Lite: Task-Specific Knowledge Distillation from Large Vision-Language Models to Lightweight Networks—0
AVQACL: A Novel Benchmark for Audio-Visual Question Answering Continual LearningCode0
Closest Neighbors are Harmful for Lightweight Masked Auto-encodersCode0
Targeted Forgetting of Image Subgroups in CLIP Models—0
Distilling Spatially-Heterogeneous Distortion Perception for Blind Image Quality Assessment—0
BiM-VFI: Bidirectional Motion Field-Guided Frame Interpolation for Video with Non-uniform Motions—0
Distilling Monocular Foundation Model for Fine-grained Depth Completion—0
ADU: Adaptive Detection of Unknown Categories in Black-Box Domain Adaptation—0
CoMBO: Conflict Mitigation via Branched Optimization for Class Incremental Segmentation—0
Random Conditioning for Diffusion Model Compression with Distillation—0
LENS-XAI: Redefining Lightweight and Explainable Network Security through Knowledge Distillation and Variational Autoencoders for Scalable Intrusion Detection in Cybersecurity—0
Pan-infection Foundation Framework Enables Multiple Pathogen Prediction—0
ECG-guided individual identification via PPG—0
Temporal reasoning for timeline summarisation in social media—0
Improving Acoustic Scene Classification in Low-Resource Conditions—0
Invariant debiasing learning for recommendation via biased imputationCode0
Learning an Adaptive and View-Invariant Vision Transformer for Real-Time UAV TrackingCode2
Injecting Explainability and Lightweight Design into Weakly Supervised Video Anomaly Detection Systems—0
Feature Alignment-Based Knowledge Distillation for Efficient Compression of Large Language Models—0
Asymmetrical Reciprocity-based Federated Learning for Resolving Disparities in Medical DiagnosisCode0
SpectralKD: A Unified Framework for Interpreting and Distilling Vision Transformers via Spectral AnalysisCode0
HTR-JAND: Handwritten Text Recognition with Joint Attention Network and Knowledge DistillationCode0
Better Knowledge Enhancement for Privacy-Preserving Cross-Project Defect Prediction—0
Exploiting Label Skewness for Spiking Neural Networks in Federated Learning—0
Distilling Large Language Models for Efficient Clinical Information Extraction—0
Cross-View Consistency Regularisation for Knowledge DistillationCode0
CBNN: 3-Party Secure Framework for Customized Binary Neural Networks Inference—0
STKDRec: Spatial-Temporal Knowledge Distillation for Takeaway RecommendationCode0
LiRCDepth: Lightweight Radar-Camera Depth Estimation via Knowledge Distillation and Uncertainty GuidanceCode1
BabyHGRN: Exploring RNNs for Sample-Efficient Training of Language Models—0
A New Method to Capturing Compositional Knowledge in Linguistic Space—0
Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion ModelsCode1
Uncertainty-Guided Cross Attention Ensemble Mean Teacher for Semi-supervised Medical Image SegmentationCode0
Self-Evolution Knowledge Distillation for LLM-based Machine Translation—0
Multi-Level Optimal Transport for Universal Cross-Tokenizer Knowledge Distillation on Language ModelsCode1
Show:102550
← PrevPage 9 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