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 651–700 of 4240 papers

TitleStatusHype
Efficient and Robust Knowledge Distillation from A Stronger Teacher Based on Correlation Matching—0
KnowledgeSG: Privacy-Preserving Synthetic Text Generation with Knowledge Distillation from ServerCode0
Progressive distillation induces an implicit curriculum—0
ReasoningRank: Teaching Student Models to Rank through Reasoning-Based Knowledge Distillation—0
DAdEE: Unsupervised Domain Adaptation in Early Exit PLMsCode0
CAPEEN: Image Captioning with Early Exits and Knowledge DistillationCode0
DiDOTS: Knowledge Distillation from Large-Language-Models for Dementia Obfuscation in Transcribed Speech—0
Distillation-Free One-Step Diffusion for Real-World Image Super-ResolutionCode2
Accelerating Diffusion Models with One-to-Many Knowledge Distillation—0
Gap Preserving Distillation by Building Bidirectional Mappings with A Dynamic Teacher—0
Self-Supervised Keypoint Detection with Distilled Depth Keypoint Representation—0
Learning from Committee: Reasoning Distillation from a Mixture of Teachers with Peer-ReviewCode2
DocKD: Knowledge Distillation from LLMs for Open-World Document Understanding Models—0
Dataset Distillation via Knowledge Distillation: Towards Efficient Self-Supervised Pre-Training of Deep NetworksCode0
BLEND: Behavior-guided Neural Population Dynamics Modeling via Privileged Knowledge DistillationCode0
PairDistill: Pairwise Relevance Distillation for Dense RetrievalCode1
PHI-S: Distribution Balancing for Label-Free Multi-Teacher Distillation—0
"No Matter What You Do": Purifying GNN Models via Backdoor UnlearningCode0
Foldable SuperNets: Scalable Merging of Transformers with Different Initializations and TasksCode0
HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard ModelsCode1
Self-Updatable Large Language Models with Parameter Integration—0
Local-to-Global Self-Supervised Representation Learning for Diabetic Retinopathy Grading—0
AMR-Evol: Adaptive Modular Response Evolution Elicits Better Knowledge Distillation for Large Language Models in Code GenerationCode0
Compressing Recurrent Neural Networks for FPGA-accelerated Implementation in Fluorescence Lifetime Imaging—0
Efficient Technical Term Translation: A Knowledge Distillation Approach for Parenthetical Terminology Translation—0
Advancing Medical Radiograph Representation Learning: A Hybrid Pre-training Paradigm with Multilevel Semantic Granularity—0
Enhancing Romanian Offensive Language Detection through Knowledge Distillation, Multi-Task Learning, and Data Augmentation—0
Classroom-Inspired Multi-Mentor Distillation with Adaptive Learning Strategies—0
HYDRA-FL: Hybrid Knowledge Distillation for Robust and Accurate Federated Learning—0
Linear Projections of Teacher Embeddings for Few-Class Distillation—0
Domain Consistency Representation Learning for Lifelong Person Re-IdentificationCode1
Tailored Federated Learning: Leveraging Direction Regulation & Knowledge Distillation—0
InfantCryNet: A Data-driven Framework for Intelligent Analysis of Infant Cries—0
Mind the Gap: Promoting Missing Modality Brain Tumor Segmentation with Alignment—0
Multi-modal Cross-domain Self-supervised Pre-training for fMRI and EEG Fusion—0
Semi-Supervised Bone Marrow Lesion Detection from Knee MRI Segmentation Using Mask Inpainting Models—0
Student-Oriented Teacher Knowledge Refinement for Knowledge Distillation—0
Towards Diverse Device Heterogeneous Federated Learning via Task Arithmetic Knowledge IntegrationCode0
MiniVLN: Efficient Vision-and-Language Navigation by Progressive Knowledge Distillation—0
Harmonizing knowledge Transfer in Neural Network with Unified Distillation—0
Kendall's τ Coefficient for Logits Distillation—0
Weak-to-Strong Backdoor Attack for Large Language Models—0
Shape-intensity knowledge distillation for robust medical image segmentationCode0
MT2KD: Towards A General-Purpose Encoder for Speech, Speaker, and Audio Events—0
Adverse Weather Optical Flow: Cumulative Homogeneous-Heterogeneous Adaptation—0
SelectiveKD: A semi-supervised framework for cancer detection in DBT through Knowledge Distillation and Pseudo-labeling—0
Privacy Evaluation Benchmarks for NLP ModelsCode0
AIM 2024 Challenge on UHD Blind Photo Quality AssessmentCode1
Twin Network Augmentation: A Novel Training Strategy for Improved Spiking Neural Networks and Efficient Weight Quantization—0
TS-HTFA: Advancing Time Series Forecasting via Hierarchical Text-Free Alignment with Large Language Models—0
Show:102550
← PrevPage 14 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