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
A Fast Knowledge Distillation Framework for Visual RecognitionCode1
Distilling Holistic Knowledge with Graph Neural NetworksCode1
Contrastive Distillation on Intermediate Representations for Language Model CompressionCode1
Distilling Image Classifiers in Object DetectorsCode1
Geometer: Graph Few-Shot Class-Incremental Learning via Prototype RepresentationCode1
Contrastive Representation DistillationCode1
Prototype-based Incremental Few-Shot Semantic SegmentationCode1
Distilling Knowledge from Ensembles of Acoustic Models for Joint CTC-Attention End-to-End Speech RecognitionCode1
Contrastive Deep SupervisionCode1
COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using TransformersCode1
Distilling Knowledge from Self-Supervised Teacher by Embedding Graph AlignmentCode1
Communication-Efficient Federated Learning through Adaptive Weight Clustering and Server-Side DistillationCode1
Distilling Linguistic Context for Language Model CompressionCode1
Distilling Large Vision-Language Model with Out-of-Distribution GeneralizabilityCode1
GenFormer -- Generated Images are All You Need to Improve Robustness of Transformers on Small DatasetsCode1
Distilling Meta Knowledge on Heterogeneous Graph for Illicit Drug Trafficker Detection on Social MediaCode1
Geometric Knowledge Distillation: Topology Compression for Graph Neural NetworksCode1
Distilling Object Detectors via Decoupled FeaturesCode1
Distilling Object Detectors with Feature RichnessCode1
Knowledge Distillation via Route Constrained OptimizationCode1
Grad-CAM++: Improved Visual Explanations for Deep Convolutional NetworksCode1
Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge DistillationCode1
Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse DataCode1
Distilling the Knowledge in a Neural NetworkCode1
Complementary Relation Contrastive DistillationCode1
LabelDistill: Label-guided Cross-modal Knowledge Distillation for Camera-based 3D Object DetectionCode1
Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation?Code1
Label Poisoning is All You NeedCode1
Generative Bias for Robust Visual Question AnsweringCode1
A Discrepancy Aware Framework for Robust Anomaly DetectionCode1
Continual Learning for Image Segmentation with Dynamic QueryCode1
Comprehensive Knowledge Distillation with Causal InterventionCode1
Distill on the Go: Online knowledge distillation in self-supervised learningCode1
Distill the Image to Nowhere: Inversion Knowledge Distillation for Multimodal Machine TranslationCode1
DistilProtBert: A distilled protein language model used to distinguish between real proteins and their randomly shuffled counterpartsCode1
DistilPose: Tokenized Pose Regression with Heatmap DistillationCode1
Generative Model-based Feature Knowledge Distillation for Action RecognitionCode1
AgeFlow: Conditional Age Progression and Regression with Normalizing FlowsCode1
Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box PredictorsCode1
Distributed Dynamic Map Fusion via Federated Learning for Intelligent Networked VehiclesCode1
ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via α-β-DivergenceCode1
DisWOT: Student Architecture Search for Distillation WithOut TrainingCode1
Distribution-aware Knowledge Prototyping for Non-exemplar Lifelong Person Re-identificationCode1
Distribution-aware Forgetting Compensation for Exemplar-Free Lifelong Person Re-identificationCode1
Continual evaluation for lifelong learning: Identifying the stability gapCode1
DKDL-Net: A Lightweight Bearing Fault Detection Model via Decoupled Knowledge Distillation and Low-Rank Adaptation Fine-tuningCode1
DM-VTON: Distilled Mobile Real-time Virtual Try-OnCode1
Computation-Efficient Knowledge Distillation via Uncertainty-Aware MixupCode1
DnS: Distill-and-Select for Efficient and Accurate Video Indexing and RetrievalCode1
Creating Something from Nothing: Unsupervised Knowledge Distillation for Cross-Modal HashingCode1
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