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 1651–1700 of 4240 papers

TitleStatusHype
Distilling Image Dehazing With Heterogeneous Task ImitationCode0
GSB: Group Superposition Binarization for Vision Transformer with Limited Training SamplesCode0
Guiding Frame-Level CTC Alignments Using Self-knowledge DistillationCode0
SFT-KD-Recon: Learning a Student-friendly Teacher for Knowledge Distillation in Magnetic Resonance Image ReconstructionCode0
Greedy-layer Pruning: Speeding up Transformer Models for Natural Language ProcessingCode0
Distilling Global and Local Logits With Densely Connected RelationsCode0
Cross-View Consistency Regularisation for Knowledge DistillationCode0
FM2DS: Few-Shot Multimodal Multihop Data Synthesis with Knowledge Distillation for Question AnsweringCode0
Graph Knowledge Distillation to Mixture of ExpertsCode0
Distilling Focal Knowledge From Imperfect Expert for 3D Object DetectionCode0
Camera-Incremental Object Re-Identification with Identity Knowledge EvolutionCode0
Graph Entropy Minimization for Semi-supervised Node ClassificationCode0
Graph-based Knowledge Distillation by Multi-head Attention NetworkCode0
Gradient Knowledge Distillation for Pre-trained Language ModelsCode0
Group Multi-View Transformer for 3D Shape Analysis with Spatial EncodingCode0
Annealing Knowledge DistillationCode0
Foundation Models for Structural Health MonitoringCode0
Distilling and Transferring Knowledge via cGAN-generated Samples for Image Classification and RegressionCode0
Spending Your Winning Lottery Better After Drawing ItCode0
Goal-Conditioned Q-Learning as Knowledge DistillationCode0
A Comprehensive Overhaul of Feature DistillationCode0
GNN's Uncertainty Quantification using Self-DistillationCode0
Goldfish: An Efficient Federated Unlearning FrameworkCode0
GLiRA: Black-Box Membership Inference Attack via Knowledge DistillationCode0
Distilled Non-Semantic Speech Embeddings with Binary Neural Networks for Low-Resource DevicesCode0
Distilled Neural Networks for Efficient Learning to RankCode0
CADIS: Handling Cluster-skewed Non-IID Data in Federated Learning with Clustered Aggregation and Knowledge DIStilled RegularizationCode0
Distilled Gradual Pruning with Pruned Fine-tuningCode0
GKT: A Novel Guidance-Based Knowledge Transfer Framework For Efficient Cloud-edge Collaboration LLM DeploymentCode0
Distilled GPT for Source Code SummarizationCode0
cViL: Cross-Lingual Training of Vision-Language Models using Knowledge DistillationCode0
Preference-Consistent Knowledge Distillation for Recommender SystemCode0
A Diffusion Model and Knowledge Distillation Framework for Robust Coral Detection in Complex Underwater EnvironmentsCode0
GKD: Semi-supervised Graph Knowledge Distillation for Graph-Independent InferenceCode0
GLANCE: Global to Local Architecture-Neutral Concept-based ExplanationsCode0
GOTHAM: Graph Class Incremental Learning Framework under Weak SupervisionCode0
Distill-DBDGAN: Knowledge Distillation and Adversarial Learning Framework for Defocus Blur DetectionCode0
DistillCSE: Distilled Contrastive Learning for Sentence EmbeddingsCode0
Exploiting the Semantic Knowledge of Pre-trained Text-Encoders for Continual LearningCode0
Generative Denoise Distillation: Simple Stochastic Noises Induce Efficient Knowledge Transfer for Dense PredictionCode0
DAdEE: Unsupervised Domain Adaptation in Early Exit PLMsCode0
BEiT v2: Masked Image Modeling with Vector-Quantized Visual TokenizersCode0
FS-BAN: Born-Again Networks for Domain Generalization Few-Shot ClassificationCode0
DAD++: Improved Data-free Test Time Adversarial DefenseCode0
Distillation Techniques for Pseudo-rehearsal Based Incremental LearningCode0
Generalizing Teacher Networks for Effective Knowledge Distillation Across Student ArchitecturesCode0
Generalization Matters: Loss Minima Flattening via Parameter Hybridization for Efficient Online Knowledge DistillationCode0
Structural Knowledge Distillation: Tractably Distilling Information for Structured PredictorCode0
Generalized Knowledge Distillation via Relationship MatchingCode0
Generate, Annotate, and Learn: NLP with Synthetic TextCode0
Show:102550
← PrevPage 34 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