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 251–300 of 4240 papers

TitleStatusHype
Cross-modality Data Augmentation for End-to-End Sign Language TranslationCode1
DnS: Distill-and-Select for Efficient and Accurate Video Indexing and RetrievalCode1
A Deep Knowledge Distillation framework for EEG assisted enhancement of single-lead ECG based sleep stagingCode1
Does Knowledge Distillation Really Work?Code1
CSAKD: Knowledge Distillation with Cross Self-Attention for Hyperspectral and Multispectral Image FusionCode1
AICSD: Adaptive Inter-Class Similarity Distillation for Semantic SegmentationCode1
CrossMatch: Enhance Semi-Supervised Medical Image Segmentation with Perturbation Strategies and Knowledge DistillationCode1
Cross-Modal Fusion Distillation for Fine-Grained Sketch-Based Image RetrievalCode1
CTC-based Non-autoregressive Textless Speech-to-Speech TranslationCode1
DASS: Distilled Audio State Space Models Are Stronger and More Duration-Scalable LearnersCode1
Agree to Disagree: Adaptive Ensemble Knowledge Distillation in Gradient SpaceCode1
CrossKD: Cross-Head Knowledge Distillation for Object DetectionCode1
AGKD-BML: Defense Against Adversarial Attack by Attention Guided Knowledge Distillation and Bi-directional Metric LearningCode1
Cross-category Video Highlight Detection via Set-based LearningCode1
Cross-Layer Distillation with Semantic CalibrationCode1
Aggretriever: A Simple Approach to Aggregate Textual Representations for Robust Dense Passage RetrievalCode1
Contrastive Model Inversion for Data-Free Knowledge DistillationCode1
Contrastive Representation DistillationCode1
Contrastive Deep SupervisionCode1
AdaDistill: Adaptive Knowledge Distillation for Deep Face RecognitionCode1
Contrastive Distillation on Intermediate Representations for Language Model CompressionCode1
Creating Something from Nothing: Unsupervised Knowledge Distillation for Cross-Modal HashingCode1
Cross-Level Distillation and Feature Denoising for Cross-Domain Few-Shot ClassificationCode1
Data Diversification: A Simple Strategy For Neural Machine TranslationCode1
Continual All-in-One Adverse Weather Removal with Knowledge Replay on a Unified Network StructureCode1
Context-Aware Image Inpainting with Learned Semantic PriorsCode1
Continual Collaborative Distillation for Recommender SystemCode1
ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via α-β-DivergenceCode1
AgeFlow: Conditional Age Progression and Regression with Normalizing FlowsCode1
Content-Variant Reference Image Quality Assessment via Knowledge DistillationCode1
Continual evaluation for lifelong learning: Identifying the stability gapCode1
ConStyle v2: A Strong Prompter for All-in-One Image RestorationCode1
Consistent Representation Learning for Continual Relation ExtractionCode1
Designing Large Foundation Models for Efficient Training and Inference: A SurveyCode1
A framework for benchmarking class-out-of-distribution detection and its application to ImageNetCode1
Consensual Collaborative Training And Knowledge Distillation Based Facial Expression Recognition Under Noisy AnnotationsCode1
Content-Aware GAN CompressionCode1
Continual Learning for Image Segmentation with Dynamic QueryCode1
Confidence-Aware Multi-Teacher Knowledge DistillationCode1
Conformer and Blind Noisy Students for Improved Image Quality AssessmentCode1
Computation-Efficient Knowledge Distillation via Uncertainty-Aware MixupCode1
Prototype-based Incremental Few-Shot Semantic SegmentationCode1
ConcealGS: Concealing Invisible Copyright Information in 3D Gaussian SplattingCode1
CoNMix for Source-free Single and Multi-target Domain AdaptationCode1
A Fast Knowledge Distillation Framework for Visual RecognitionCode1
Comprehensive Knowledge Distillation with Causal InterventionCode1
Adversarially Robust DistillationCode1
Complementary Relation Contrastive DistillationCode1
Compressing Deep Graph Neural Networks via Adversarial Knowledge DistillationCode1
ConNER: Consistency Training for Cross-lingual Named Entity RecognitionCode1
Show:102550
← PrevPage 6 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