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 201–250 of 4240 papers

TitleStatusHype
KD^2M: An unifying framework for feature knowledge distillation—0
Style over Substance: Distilled Language Models Reason Via Stylistic Replication—0
A Novel Approach To Implementing Knowledge Distillation In Tsetlin Machines—0
OccludeNeRF: Geometric-aware 3D Scene Inpainting with Collaborative Score Distillation in NeRF—0
Global Intervention and Distillation for Federated Out-of-Distribution Generalization—0
Adversarial Curriculum Graph-Free Knowledge Distillation for Graph Neural Networks—0
Is LLM the Silver Bullet to Low-Resource Languages Machine Translation?—0
Unimodal-driven Distillation in Multimodal Emotion Recognition with Dynamic Fusion—0
Crossmodal Knowledge Distillation with WordNet-Relaxed Text Embeddings for Robust Image Classification—0
A Plasticity-Aware Method for Continual Self-Supervised Learning in Remote Sensing—0
Multi-modal Knowledge Distillation-based Human Trajectory ForecastingCode1
Efficient Verified Machine Unlearning For Distillation—0
Intrinsic Image Decomposition for Robust Self-supervised Monocular Depth Estimation on Reflective Surfaces—0
Delving Deep into Semantic Relation Distillation—0
Alleviating LLM-based Generative Retrieval Hallucination in Alipay Search—0
DuckSegmentation: A segmentation model based on the AnYue Hemp Duck Dataset—0
Small Object Detection: A Comprehensive Survey on Challenges, Techniques and Real-World Applications—0
MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation—0
Modality-Independent Brain Lesion Segmentation with Privacy-aware Continual LearningCode0
Scaling Down Text Encoders of Text-to-Image Diffusion ModelsCode2
Plug-and-Play Interpretable Responsible Text-to-Image Generation via Dual-Space Multi-facet Concept Control—0
Distilling Stereo Networks for Performant and Efficient Leaner NetworksCode0
FedSKD: Aggregation-free Model-heterogeneous Federated Learning using Multi-dimensional Similarity Knowledge Distillation—0
CustomKD: Customizing Large Vision Foundation for Edge Model Improvement via Knowledge Distillation—0
OmniScience: A Domain-Specialized LLM for Scientific Reasoning and Discovery—0
Efficient Intent-Based Filtering for Multi-Party Conversations Using Knowledge Distillation from LLMs—0
Improving Acoustic Scene Classification with City Features—0
Efficient Knowledge Distillation via Curriculum Extraction—0
InhibiDistilbert: Knowledge Distillation for a ReLU and Addition-based Transformer—0
Advancing Deep Learning through Probability Engineering: A Pragmatic Paradigm for Modern AI—0
DCA: Dividing and Conquering Amnesia in Incremental Object DetectionCode0
Technical Report for the 5th CLVision Challenge at CVPR: Addressing the Class-Incremental with Repetition using Unlabeled Data -- 4th Place SolutionCode0
KoGNER: A Novel Framework for Knowledge Graph Distillation on Biomedical Named Entity Recognition—0
High Temporal Consistency through Semantic Similarity Propagation in Semi-Supervised Video Semantic Segmentation for Autonomous FlightCode1
Distilling 3D distinctive local descriptors for 6D pose estimation—0
Ensemble Knowledge Distillation for Machine Learning Interatomic Potentials—0
Scale-Aware Contrastive Reverse Distillation for Unsupervised Medical Anomaly DetectionCode0
SCJD: Sparse Correlation and Joint Distillation for Efficient 3D Human Pose EstimationCode0
Uncertainty-Aware Knowledge Distillation for Compact and Efficient 6DoF Pose Estimation—0
Real-Time Cell Sorting with Scalable In Situ FPGA-Accelerated Deep LearningCode0
A Comprehensive Survey on Knowledge DistillationCode2
Enabling Weak Client Participation via On-device Knowledge Distillation in Heterogenous Federated Learning—0
Exploring Performance-Complexity Trade-Offs in Sound Event Detection ModelsCode1
Creating a Good Teacher for Knowledge Distillation in Acoustic Scene Classification—0
Adaptive Temperature Based on Logits Correlation in Knowledge DistillationCode0
CleverDistiller: Simple and Spatially Consistent Cross-modal Distillation—0
xVLM2Vec: Adapting LVLM-based embedding models to multilinguality using Self-Knowledge Distillation—0
Vi-LAD: Vision-Language Attention Distillation for Socially-Aware Robot Navigation in Dynamic Environments—0
Unified Locomotion Transformer with Simultaneous Sim-to-Real Transfer for Quadrupeds—0
LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference OptimizationCode2
Show:102550
← PrevPage 5 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