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 2151–2200 of 4240 papers

TitleStatusHype
KS-DETR: Knowledge Sharing in Attention Learning for Detection TransformerCode0
Debiased Distillation by Transplanting the Last Layer—0
FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge ComputingCode1
Two-in-one Knowledge Distillation for Efficient Facial Forgery Detection—0
The Role of Masking for Efficient Supervised Knowledge Distillation of Vision Transformers—0
CADIS: Handling Cluster-skewed Non-IID Data in Federated Learning with Clustered Aggregation and Knowledge DIStilled RegularizationCode0
Social4Rec: Distilling User Preference from Social Graph for Video Recommendation in TencentCode2
HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained Transformers—0
RobustDistiller: Compressing Universal Speech Representations for Enhanced Environment Robustness—0
Fairly Predicting Graft Failure in Liver Transplant for Organ Assigning—0
Explicit and Implicit Knowledge Distillation via Unlabeled Data—0
Few-shot 3D LiDAR Semantic Segmentation for Autonomous Driving—0
ST-MFNet Mini: Knowledge Distillation-Driven Frame InterpolationCode0
Fuzzy Knowledge Distillation from High-Order TSK to Low-Order TSK—0
Cross Modal Distillation for Flood Extent Mapping—0
LEALLA: Learning Lightweight Language-agnostic Sentence Embeddings with Knowledge Distillation—0
Learning From Biased Soft Labels—0
New Insights on Relieving Task-Recency Bias for Online Class Incremental LearningCode0
A lightweight network for photovoltaic cell defect detection in electroluminescence images based on neural architecture search and knowledge distillation—0
Offline-to-Online Knowledge Distillation for Video Instance Segmentation—0
Multi-teacher knowledge distillation as an effective method for compressing ensembles of neural networksCode1
Take a Prior from Other Tasks for Severe Blur Removal—0
PerAda: Parameter-Efficient Federated Learning Personalization with Generalization GuaranteesCode1
Learning from Noisy Crowd Labels with LogicsCode0
Exploring Navigation Maps for Learning-Based Motion PredictionCode1
NYCU-TWO at Memotion 3: Good Foundation, Good Teacher, then you have Good Meme Analysis—0
SCLIFD:Supervised Contrastive Knowledge Distillation for Incremental Fault Diagnosis under Limited Fault Data—0
Jaccard Metric Losses: Optimizing the Jaccard Index with Soft LabelsCode1
Dual Relation Knowledge Distillation for Object DetectionCode1
Feature Affinity Assisted Knowledge Distillation and Quantization of Deep Neural Networks on Label-Free Data—0
CEN-HDR: Computationally Efficient neural Network for real-time High Dynamic Range imagingCode1
SOCRATES: Text-based Human Search and Approach using a Robot Dog—0
Toward Extremely Lightweight Distracted Driver Recognition With Distillation-Based Neural Architecture Search and Knowledge TransferCode0
Lightweight Transformers for Clinical Natural Language ProcessingCode1
Knowledge Distillation-based Information Sharing for Online Process Monitoring in Decentralized Manufacturing System—0
Enhancing Modality-Agnostic Representations via Meta-Learning for Brain Tumor Segmentation—0
SLaM: Student-Label Mixing for Distillation with Unlabeled Examples—0
An Empirical Study of Uniform-Architecture Knowledge Distillation in Document Ranking—0
Audio Representation Learning by Distilling Video as Privileged Information—0
Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning—0
Knowledge Distillation in Vision Transformers: A Critical Review—0
Revisiting Intermediate Layer Distillation for Compressing Language Models: An Overfitting PerspectiveCode0
Enhancing Once-For-All: A Study on Parallel Blocks, Skip Connections and Early Exits—0
Generalized Uncertainty of Deep Neural Networks: Taxonomy and Applications—0
Distill-DBDGAN: Knowledge Distillation and Adversarial Learning Framework for Defocus Blur DetectionCode0
Adaptive Search-and-Training for Robust and Efficient Network PruningCode0
Knowledge Distillation on Graphs: A Survey—0
Continual Segment: Towards a Single, Unified and Accessible Continual Segmentation Model of 143 Whole-body Organs in CT Scans—0
Improved Knowledge Distillation for Pre-trained Language Models via Knowledge Selection—0
AMD: Adaptive Masked Distillation for Object Detection—0
Show:102550
← PrevPage 44 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