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 851–900 of 4240 papers

TitleStatusHype
Distill on the Go: Online knowledge distillation in self-supervised learningCode1
Real-time Event Recognition of Long-distance Distributed Vibration Sensing with Knowledge Distillation and Hardware AccelerationCode1
DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech TranslationCode1
DASS: Distilled Audio State Space Models Are Stronger and More Duration-Scalable LearnersCode1
Data Diversification: A Simple Strategy For Neural Machine TranslationCode1
Better Estimation of the KL Divergence Between Language ModelsCode1
Refine Myself by Teaching Myself: Feature Refinement via Self-Knowledge DistillationCode1
Regularizing Class-wise Predictions via Self-knowledge DistillationCode1
Data Efficient Language-supervised Zero-shot Recognition with Optimal Transport DistillationCode1
Distilled Split Deep Neural Networks for Edge-Assisted Real-Time SystemsCode1
Distilled Semantics for Comprehensive Scene Understanding from VideosCode1
Going Beyond Classification Accuracy Metrics in Model CompressionCode1
Adjoined Networks: A Training Paradigm with Applications to Network CompressionCode1
Data-Free Class-Incremental Hand Gesture RecognitionCode1
BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object DetectionCode1
Rethinking Centered Kernel Alignment in Knowledge DistillationCode1
BEV-LGKD: A Unified LiDAR-Guided Knowledge Distillation Framework for BEV 3D Object DetectionCode1
Distilling a Powerful Student Model via Online Knowledge DistillationCode1
SimDistill: Simulated Multi-modal Distillation for BEV 3D Object DetectionCode1
Rethinking Momentum Knowledge Distillation in Online Continual LearningCode1
Data-Free Knowledge Distillation for Heterogeneous Federated LearningCode1
Distilling Visual Priors from Self-Supervised LearningCode1
Return of the Encoder: Maximizing Parameter Efficiency for SLMsCode1
Reverse Knowledge Distillation: Training a Large Model using a Small One for Retinal Image Matching on Limited DataCode1
Beyond Generic: Enhancing Image Captioning with Real-World Knowledge using Vision-Language Pre-Training ModelCode1
Data-Free Knowledge Distillation via Feature Exchange and Activation Region ConstraintCode1
Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT CompressionCode1
Revisiting Prototypical Network for Cross Domain Few-Shot LearningCode1
A Neural Span-Based Continual Named Entity Recognition ModelCode1
Beyond Self-Supervision: A Simple Yet Effective Network Distillation Alternative to Improve BackbonesCode1
AlphaFold Distillation for Protein DesignCode1
Robust Spatiotemporal Traffic Forecasting with Reinforced Dynamic Adversarial TrainingCode1
Distill the Image to Nowhere: Inversion Knowledge Distillation for Multimodal Machine TranslationCode1
DA-Mamba: Domain Adaptive Hybrid Mamba-Transformer Based One-Stage Object DetectionCode1
ROSITA: Refined BERT cOmpreSsion with InTegrAted techniquesCode1
Distilling Script Knowledge from Large Language Models for Constrained Language PlanningCode1
Distilling Out-of-Distribution Robustness from Vision-Language Foundation ModelsCode1
Distilling DETR with Visual-Linguistic Knowledge for Open-Vocabulary Object DetectionCode1
Distilling the Knowledge in a Neural NetworkCode1
Distilling Object Detectors via Decoupled FeaturesCode1
BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge DistillationCode1
Scaling Sparse and Dense Retrieval in Decoder-Only LLMsCode1
AltDiffusion: A Multilingual Text-to-Image Diffusion ModelCode1
SCPNet: Semantic Scene Completion on Point CloudCode1
Distilling Object Detectors with Feature RichnessCode1
Always Clear Depth: Robust Monocular Depth Estimation under Adverse WeatherCode1
Bi-directional Weakly Supervised Knowledge Distillation for Whole Slide Image ClassificationCode1
Distilling Image Classifiers in Object DetectorsCode1
Self-Supervised Adaptation for Video Super-ResolutionCode1
Distilling the Knowledge of BERT for Sequence-to-Sequence ASRCode1
Show:102550
← PrevPage 18 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