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
FedMD: Heterogenous Federated Learning via Model DistillationCode1
FedNoRo: Towards Noise-Robust Federated Learning by Addressing Class Imbalance and Label Noise HeterogeneityCode1
Data-Free Network Quantization With Adversarial Knowledge DistillationCode1
Data-Free Knowledge Distillation via Feature Exchange and Activation Region ConstraintCode1
DualFair: Fair Representation Learning at Both Group and Individual Levels via Contrastive Self-supervisionCode1
Balanced Knowledge Distillation for Long-tailed LearningCode1
Decoupled Kullback-Leibler Divergence LossCode1
Few-Shot Class-Incremental Learning via Class-Aware Bilateral DistillationCode1
CheXseg: Combining Expert Annotations with DNN-generated Saliency Maps for X-ray SegmentationCode1
Fitting Auditory Filterbanks with Multiresolution Neural NetworksCode1
Chinese grammatical error correction based on knowledge distillationCode1
Decomposed Knowledge Distillation for Class-Incremental Semantic SegmentationCode1
Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual InformationCode1
DeepAqua: Self-Supervised Semantic Segmentation of Wetland Surface Water Extent with SAR Images using Knowledge DistillationCode1
Deliberation on Priors: Trustworthy Reasoning of Large Language Models on Knowledge GraphsCode1
BearingPGA-Net: A Lightweight and Deployable Bearing Fault Diagnosis Network via Decoupled Knowledge Distillation and FPGA AccelerationCode1
Circumventing Outliers of AutoAugment with Knowledge DistillationCode1
Are Intermediate Layers and Labels Really Necessary? A General Language Model Distillation MethodCode1
Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine TranslationCode1
General Cyclical Training of Neural NetworksCode1
Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language ModelCode1
DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation TrainerCode1
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
Deep Structured Instance Graph for Distilling Object DetectorsCode1
Deformation Flow Based Two-Stream Network for Lip ReadingCode1
Generative Model-based Feature Knowledge Distillation for Action RecognitionCode1
Adjoined Networks: A Training Paradigm with Applications to Network CompressionCode1
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
Densely Guided Knowledge Distillation using Multiple Teacher AssistantsCode1
DE-RRD: A Knowledge Distillation Framework for Recommender SystemCode1
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
Channel-wise Knowledge Distillation for Dense PredictionCode1
AlphaFold Distillation for Protein DesignCode1
Distribution-aware Knowledge Prototyping for Non-exemplar Lifelong Person Re-identificationCode1
DGEKT: A Dual Graph Ensemble Learning Method for Knowledge TracingCode1
DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue GenerationCode1
Dice Semimetric Losses: Optimizing the Dice Score with Soft LabelsCode1
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
Extending global-local view alignment for self-supervised learning with remote sensing imageryCode1
Channel Distillation: Channel-Wise Attention for Knowledge 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