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 451–500 of 4240 papers

TitleStatusHype
FedACK: Federated Adversarial Contrastive Knowledge Distillation for Cross-Lingual and Cross-Model Social Bot DetectionCode1
Enhancing Low-resolution Face Recognition with Feature Similarity Knowledge DistillationCode1
DistilPose: Tokenized Pose Regression with Heatmap DistillationCode1
Distillation from Heterogeneous Models for Top-K RecommendationCode1
Towards Activated Muscle Group Estimation in the WildCode1
Generic-to-Specific Distillation of Masked AutoencodersCode1
Graph-based Knowledge Distillation: A survey and experimental evaluationCode1
A framework for benchmarking class-out-of-distribution detection and its application to ImageNetCode1
A Neural Span-Based Continual Named Entity Recognition ModelCode1
CEKD: Cross-Modal Edge-Privileged Knowledge Distillation for Semantic Scene Understanding Using Only Thermal ImagesCode1
FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge ComputingCode1
Multi-teacher knowledge distillation as an effective method for compressing ensembles of neural networksCode1
Exploring Navigation Maps for Learning-Based Motion PredictionCode1
PerAda: Parameter-Efficient Federated Learning Personalization with Generalization GuaranteesCode1
Dual Relation Knowledge Distillation for Object DetectionCode1
Jaccard Metric Losses: Optimizing the Jaccard Index with Soft LabelsCode1
CEN-HDR: Computationally Efficient neural Network for real-time High Dynamic Range imagingCode1
Lightweight Transformers for Clinical Natural Language ProcessingCode1
Knowledge Transfer from Pre-trained Language Models to Cif-based Speech Recognizers via Hierarchical DistillationCode1
OvarNet: Towards Open-vocabulary Object Attribute RecognitionCode1
Online Hyperparameter Optimization for Class-Incremental LearningCode1
TinyHD: Efficient Video Saliency Prediction with Heterogeneous Decoders using Hierarchical Maps DistillationCode1
Reference Twice: A Simple and Unified Baseline for Few-Shot Instance SegmentationCode1
Remembering Normality: Memory-guided Knowledge Distillation for Unsupervised Anomaly DetectionCode1
Dual Learning with Dynamic Knowledge Distillation for Partially Relevant Video RetrievalCode1
Few-Shot Class-Incremental Learning via Class-Aware Bilateral DistillationCode1
Data-Free Knowledge Distillation via Feature Exchange and Activation Region ConstraintCode1
Revisiting Prototypical Network for Cross Domain Few-Shot LearningCode1
Multi-Level Logit DistillationCode1
Label-Guided Knowledge Distillation for Continual Semantic Segmentation on 2D Images and 3D Point CloudsCode1
Data-Free Class-Incremental Hand Gesture RecognitionCode1
Distilling DETR with Visual-Linguistic Knowledge for Open-Vocabulary Object DetectionCode1
Discriminator-Cooperated Feature Map Distillation for GAN CompressionCode1
Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental LearningCode1
NeRN -- Learning Neural Representations for Neural NetworksCode1
Learning Object-level Point Augmentor for Semi-supervised 3D Object DetectionCode1
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?Code1
Gradient-based Intra-attention Pruning on Pre-trained Language ModelsCode1
Towards Practical Plug-and-Play Diffusion ModelsCode1
Enhancing Low-Density EEG-Based Brain-Computer Interfaces with Similarity-Keeping Knowledge DistillationCode1
FedUKD: Federated UNet Model with Knowledge Distillation for Land Use Classification from Satellite and Street ViewsCode1
Improving Simultaneous Machine Translation with Monolingual DataCode1
BEV-LGKD: A Unified LiDAR-Guided Knowledge Distillation Framework for BEV 3D Object DetectionCode1
Knowledge Distillation based Degradation Estimation for Blind Super-ResolutionCode1
Curriculum Temperature for Knowledge DistillationCode1
Dense Interspecies Face EmbeddingCode1
Unbiased Knowledge Distillation for RecommendationCode1
Look Around and Refer: 2D Synthetic Semantics Knowledge Distillation for 3D Visual GroundingCode1
XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation LearningCode1
MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous AttentionCode1
Show:102550
← PrevPage 10 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