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 401–450 of 4240 papers

TitleStatusHype
Backdoor Attacks on Self-Supervised LearningCode1
Backdoor Cleansing with Unlabeled DataCode1
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language GuidanceCode1
End-to-End Zero-Shot HOI Detection via Vision and Language Knowledge DistillationCode1
Enhancing and Adapting in the Clinic: Source-free Unsupervised Domain Adaptation for Medical Image EnhancementCode1
Enhancing Cross-Tokenizer Knowledge Distillation with Contextual Dynamical MappingCode1
A semi-supervised Teacher-Student framework for surgical tool detection and localizationCode1
Cross-Level Distillation and Feature Denoising for Cross-Domain Few-Shot ClassificationCode1
CrossKD: Cross-Head Knowledge Distillation for Object DetectionCode1
Action knowledge for video captioning with graph neural networksCode1
C2KD: Cross-Lingual Cross-Modal Knowledge Distillation for Multilingual Text-Video RetrievalCode1
Cross-Layer Distillation with Semantic CalibrationCode1
Aligned Structured Sparsity Learning for Efficient Image Super-ResolutionCode1
Evolving Search Space for Neural Architecture SearchCode1
Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual InformationCode1
CaMEL: Mean Teacher Learning for Image CaptioningCode1
Exploring Navigation Maps for Learning-Based Motion PredictionCode1
BearingPGA-Net: A Lightweight and Deployable Bearing Fault Diagnosis Network via Decoupled Knowledge Distillation and FPGA AccelerationCode1
CaKDP: Category-aware Knowledge Distillation and Pruning Framework for Lightweight 3D Object DetectionCode1
The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single ImageCode1
FAMIE: A Fast Active Learning Framework for Multilingual Information ExtractionCode1
CrossMatch: Enhance Semi-Supervised Medical Image Segmentation with Perturbation Strategies and Knowledge DistillationCode1
Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language ModelCode1
FastSpeech 2: Fast and High-Quality End-to-End Text to SpeechCode1
BERT-of-Theseus: Compressing BERT by Progressive Module ReplacingCode1
Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Large Model EnhancementCode1
Better Estimation of the KL Divergence Between Language ModelsCode1
Camera clustering for scalable stream-based active distillationCode1
Feature Structure Distillation with Centered Kernel Alignment in BERT TransferringCode1
FedACK: Federated Adversarial Contrastive Knowledge Distillation for Cross-Lingual and Cross-Model Social Bot DetectionCode1
Curriculum Temperature for Knowledge DistillationCode1
BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object DetectionCode1
BEV-LGKD: A Unified LiDAR-Guided Knowledge Distillation Framework for BEV 3D Object DetectionCode1
SimDistill: Simulated Multi-modal Distillation for BEV 3D Object DetectionCode1
Federated Learning with Extremely Noisy Clients via Negative DistillationCode1
FedMD: Heterogenous Federated Learning via Model DistillationCode1
Beyond Generic: Enhancing Image Captioning with Real-World Knowledge using Vision-Language Pre-Training ModelCode1
Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT CompressionCode1
Beyond Self-Supervision: A Simple Yet Effective Network Distillation Alternative to Improve BackbonesCode1
AlphaFold Distillation for Protein DesignCode1
Decomposed Knowledge Distillation for Class-Incremental Semantic SegmentationCode1
FerKD: Surgical Label Adaptation for Efficient DistillationCode1
Contrastive Model Inversion for Data-Free Knowledge DistillationCode1
FitNets: Hints for Thin Deep NetsCode1
BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge DistillationCode1
AltDiffusion: A Multilingual Text-to-Image Diffusion ModelCode1
Bidirectional Distillation for Top-K Recommender SystemCode1
Bi-directional Weakly Supervised Knowledge Distillation for Whole Slide Image ClassificationCode1
Contrastive Distillation on Intermediate Representations for Language Model CompressionCode1
Contrastive Representation DistillationCode1
Show:102550
← PrevPage 9 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