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 3201–3250 of 4240 papers

TitleStatusHype
Local Correlation Consistency for Knowledge Distillation—0
LoCa: Logit Calibration for Knowledge Distillation—0
Locally Linear Region Knowledge Distillation—0
Local-Selective Feature Distillation for Single Image Super-Resolution—0
Local-to-Global Self-Supervised Representation Learning for Diabetic Retinopathy Grading—0
Local vs. Global: Local Land-Use and Land-Cover Models Deliver Higher Quality Maps—0
Logic Distillation: Learning from Code Function by Function for Planning and Decision-making—0
Logits Poisoning Attack in Federated Distillation—0
LokiLM: Technical Report—0
Long Live the Lottery: The Existence of Winning Tickets in Lifelong Learning—0
Long-Range Zero-Shot Generative Deep Network Quantization—0
Long-Tailed Continual Learning For Visual Food Recognition—0
Long-tailed Food Classification—0
Hierarchical Knowledge Guided Learning for Real-world Retinal Diseases Recognition—0
Long-Tailed Question Answering in an Open World—0
Long-Term Vehicle Localization by Recursive Knowledge Distillation—0
LookALike: Human Mimicry based collaborative decision making—0
Look Backward and Forward: Self-Knowledge Distillation with Bidirectional Decoder for Neural Machine Translation—0
Look One and More: Distilling Hybrid Order Relational Knowledge for Cross-Resolution Image Recognition—0
Lost in Distillation: A Case Study in Toxicity Modeling—0
Low-Complexity Inference in Continual Learning via Compressed Knowledge Transfer—0
Low-Dimensional Federated Knowledge Graph Embedding via Knowledge Distillation—0
Low-Latency Incremental Text-to-Speech Synthesis with Distilled Context Prediction Network—0
Low-Resolution Chest X-ray Classification via Knowledge Distillation and Multi-task Learning—0
Low-resolution Face Recognition in the Wild via Selective Knowledge Distillation—0
Low-Resolution Face Recognition via Adaptable Instance-Relation Distillation—0
Low-Resolution Object Recognition with Cross-Resolution Relational Contrastive Distillation—0
Low Resource Causal Event Detection from Biomedical Literature—0
Low-resource Low-footprint Wake-word Detection using Knowledge Distillation—0
LRC-BERT: Latent-representation Contrastive Knowledge Distillation for Natural Language Understanding—0
LRSpeech: Extremely Low-Resource Speech Synthesis and Recognition—0
LTD: Low Temperature Distillation for Robust Adversarial Training—0
M2KD: Multi-model and Multi-level Knowledge Distillation for Incremental Learning—0
MadEye: Boosting Live Video Analytics Accuracy with Adaptive Camera Configurations—0
Making Neural Machine Reading Comprehension Faster—0
Making Small Language Models Better Few-Shot Learners—0
Mamba base PKD for efficient knowledge compression—0
MambaLiteSR: Image Super-Resolution with Low-Rank Mamba using Knowledge Distillation—0
Many-to-One Knowledge Distillation of Real-Time Epileptic Seizure Detection for Low-Power Wearable Internet of Things Systems—0
MapDistill: Boosting Efficient Camera-based HD Map Construction via Camera-LiDAR Fusion Model Distillation—0
Map-Free Trajectory Prediction with Map Distillation and Hierarchical Encoding—0
Marine Saliency Segmenter: Object-Focused Conditional Diffusion with Region-Level Semantic Knowledge Distillation—0
Markowitz Meets Bellman: Knowledge-distilled Reinforcement Learning for Portfolio Management—0
Masked Autoencoders Are Stronger Knowledge Distillers—0
The Role of Masking for Efficient Supervised Knowledge Distillation of Vision Transformers—0
Masked Modeling Duo for Speech: Specializing General-Purpose Audio Representation to Speech using Denoising Distillation—0
Matching Distributions between Model and Data: Cross-domain Knowledge Distillation for Unsupervised Domain Adaptation—0
Maximizing Discrimination Capability of Knowledge Distillation with Energy Function—0
Maximum Likelihood Distillation for Robust Modulation Classification—0
MCF-VC: Mitigate Catastrophic Forgetting in Class-Incremental Learning for Multimodal Video Captioning—0
Show:102550
← PrevPage 65 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