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 351–400 of 4240 papers

TitleStatusHype
Distilling Knowledge from Refinement in Multiple Instance Detection NetworksCode1
Distilling Knowledge via Knowledge ReviewCode1
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language GuidanceCode1
Compressing Deep Graph Neural Networks via Adversarial Knowledge DistillationCode1
Complementary Relation Contrastive DistillationCode1
A semi-supervised Teacher-Student framework for surgical tool detection and localizationCode1
Attention Weighted Local DescriptorsCode1
Aggretriever: A Simple Approach to Aggregate Textual Representations for Robust Dense Passage RetrievalCode1
Dynamic Knowledge Distillation for Pre-trained Language ModelsCode1
Domain Consistency Representation Learning for Lifelong Person Re-IdentificationCode1
AGKD-BML: Defense Against Adversarial Attack by Attention Guided Knowledge Distillation and Bi-directional Metric LearningCode1
Audio Embeddings as Teachers for Music ClassificationCode1
CaMEL: Mean Teacher Learning for Image CaptioningCode1
Computation-Efficient Knowledge Distillation via Uncertainty-Aware MixupCode1
CaKDP: Category-aware Knowledge Distillation and Pruning Framework for Lightweight 3D Object DetectionCode1
Agree to Disagree: Adaptive Ensemble Knowledge Distillation in Gradient SpaceCode1
Action knowledge for video captioning with graph neural networksCode1
Conformer and Blind Noisy Students for Improved Image Quality AssessmentCode1
AICSD: Adaptive Inter-Class Similarity Distillation for Semantic SegmentationCode1
CoNMix for Source-free Single and Multi-target Domain AdaptationCode1
Camera clustering for scalable stream-based active distillationCode1
Consistent Representation Learning for Continual Relation ExtractionCode1
Designing Large Foundation Models for Efficient Training and Inference: A SurveyCode1
Content-Aware GAN CompressionCode1
Channel Gating Neural NetworksCode1
Distilling Large Vision-Language Model with Out-of-Distribution GeneralizabilityCode1
AIM 2024 Challenge on UHD Blind Photo Quality AssessmentCode1
Continual All-in-One Adverse Weather Removal with Knowledge Replay on a Unified Network StructureCode1
Continual Collaborative Distillation for Recommender SystemCode1
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?Code1
AutoGAN-Distiller: Searching to Compress Generative Adversarial NetworksCode1
Continual evaluation for lifelong learning: Identifying the stability gapCode1
Distilling Visual Priors from Self-Supervised LearningCode1
Distilling Dense Representations for Ranking using Tightly-Coupled TeachersCode1
Contrastive Model Inversion for Data-Free Knowledge DistillationCode1
Cross-Level Distillation and Feature Denoising for Cross-Domain Few-Shot ClassificationCode1
DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue GenerationCode1
Learning Efficient Vision Transformers via Fine-Grained Manifold DistillationCode1
Ego-Exo: Transferring Visual Representations from Third-person to First-person VideosCode1
Eliminating Backdoor Triggers for Deep Neural Networks Using Attention Relation Graph DistillationCode1
CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models CascadeCode1
Cross-Layer Distillation with Semantic CalibrationCode1
Avatar Knowledge Distillation: Self-ensemble Teacher Paradigm with UncertaintyCode1
A Knowledge Distillation Framework For Enhancing Ear-EEG Based Sleep Staging With Scalp-EEG DataCode1
Cross-category Video Highlight Detection via Set-based LearningCode1
Creating Something from Nothing: Unsupervised Knowledge Distillation for Cross-Modal HashingCode1
Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation ModelsCode1
Distilling DETR with Visual-Linguistic Knowledge for Open-Vocabulary Object DetectionCode1
Are Intermediate Layers and Labels Really Necessary? A General Language Model Distillation MethodCode1
Bridging Cross-task Protocol Inconsistency for Distillation in Dense Object DetectionCode1
Show:102550
← PrevPage 8 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