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 801–850 of 4240 papers

TitleStatusHype
CLIP-CID: Efficient CLIP Distillation via Cluster-Instance Discrimination—0
MedMAP: Promoting Incomplete Multi-modal Brain Tumor Segmentation with Alignment—0
V2X-VLM: End-to-End V2X Cooperative Autonomous Driving Through Large Vision-Language Models—0
Multi Teacher Privileged Knowledge Distillation for Multimodal Expression RecognitionCode0
MIDAS: Multi-level Intent, Domain, And Slot Knowledge Distillation for Multi-turn NLUCode0
Towards Real-time Video Compressive Sensing on Mobile DevicesCode0
One Step Diffusion-based Super-Resolution with Time-Aware DistillationCode1
FedQUIT: On-Device Federated Unlearning via a Quasi-Competent Virtual Teacher—0
Knowledge Distillation with Refined LogitsCode1
Using Advanced LLMs to Enhance Smaller LLMs: An Interpretable Knowledge Distillation Approach—0
Optimizing Vision Transformers with Data-Free Knowledge Transfer—0
Low-Dimensional Federated Knowledge Graph Embedding via Knowledge Distillation—0
LaDiMo: Layer-wise Distillation Inspired MoEfier—0
ComKD-CLIP: Comprehensive Knowledge Distillation for Contrastive Language-Image Pre-traning Model—0
Distillation Learning Guided by Image Reconstruction for One-Shot Medical Image SegmentationCode0
Real-time Event Recognition of Long-distance Distributed Vibration Sensing with Knowledge Distillation and Hardware AccelerationCode1
Dual-Modeling Decouple Distillation for Unsupervised Anomaly Detection—0
EEGMobile: Enhancing Speed and Accuracy in EEG-Based Gaze Prediction with Advanced Mobile Architectures—0
Leveraging Entity Information for Cross-Modality Correlation Learning: The Entity-Guided Multimodal SummarizationCode0
Inference Optimizations for Large Language Models: Effects, Challenges, and Practical Considerations—0
Comb, Prune, Distill: Towards Unified Pruning for Vision Model CompressionCode0
VizECGNet: Visual ECG Image Network for Cardiovascular Diseases Classification with Multi-Modal Training and Knowledge Distillation—0
Low-Cost Self-Ensembles Based on Multi-Branch Transformation and Grouped ConvolutionCode0
An approach to optimize inference of the DIART speaker diarization pipeline—0
Unsupervised Domain Adaption Harnessing Vision-Language Pre-trainingCode1
Do You Remember . . . the Future? Weak-to-Strong generalization in 3D Object DetectionCode0
Exploiting the Semantic Knowledge of Pre-trained Text-Encoders for Continual LearningCode0
DistillGrasp: Integrating Features Correlation with Knowledge Distillation for Depth Completion of Transparent Objects—0
Sentence-wise Speech Summarization: Task, Datasets, and End-to-End Modeling with LM Knowledge Distillation—0
StyleRF-VolVis: Style Transfer of Neural Radiance Fields for Expressive Volume Visualization—0
Gemma 2: Improving Open Language Models at a Practical Size—0
Lifelong Person Search—0
Dynamic Object Queries for Transformer-based Incremental Object Detection—0
VIPeR: Visual Incremental Place Recognition with Adaptive Mining and Continual Learning—0
Learning Effective Representations for Retrieval Using Self-Distillation with Adaptive Relevance Margins—0
Pruning Large Language Models with Semi-Structural Adaptive Sparse TrainingCode1
SalNAS: Efficient Saliency-prediction Neural Architecture Search with self-knowledge distillationCode0
ActivityCLIP: Enhancing Group Activity Recognition by Mining Complementary Information from Text to Supplement Image Modality—0
Overcoming Uncertain Incompleteness for Robust Multimodal Sequential Diagnosis Prediction via Curriculum Data Erasing Guided Knowledge DistillationCode0
Mixture of Modular Experts: Distilling Knowledge from a Multilingual Teacher into Specialized Modular Language ModelsCode0
LLAVADI: What Matters For Multimodal Large Language Models Distillation—0
Logic Distillation: Learning from Code Function by Function for Planning and Decision-making—0
Sewer Image Super-Resolution with Depth Priors and Its Lightweight Network—0
Modality-Balanced Learning for Multimedia RecommendationCode1
Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D TransformersCode0
Towards A Generalizable Pathology Foundation Model via Unified Knowledge DistillationCode2
FedUD: Exploiting Unaligned Data for Cross-Platform Federated Click-Through Rate Prediction—0
Leveraging Foundation Models via Knowledge Distillation in Multi-Object Tracking: Distilling DINOv2 Features to FairMOTCode0
How to Train the Teacher Model for Effective Knowledge DistillationCode0
NC-NCD: Novel Class Discovery for Node ClassificationCode0
Show:102550
← PrevPage 17 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