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 851–900 of 4240 papers

TitleStatusHype
NC-NCD: Novel Class Discovery for Node ClassificationCode0
Separating Novel Features for Logical Anomaly Detection: A Straightforward yet Effective Approach—0
How to Train the Teacher Model for Effective Knowledge DistillationCode0
CoMoTo: Unpaired Cross-Modal Lesion Distillation Improves Breast Lesion Detection in TomosynthesisCode0
DDK: Distilling Domain Knowledge for Efficient Large Language Models—0
OriGen:Enhancing RTL Code Generation with Code-to-Code Augmentation and Self-ReflectionCode1
Generalizing Teacher Networks for Effective Knowledge Distillation Across Student ArchitecturesCode0
Comprehensive Study on Performance Evaluation and Optimization of Model Compression: Bridging Traditional Deep Learning and Large Language Models—0
Disentangling spatio-temporal knowledge for weakly supervised object detection and segmentation in surgical videoCode0
Synthetic Image Learning: Preserving Performance and Preventing Membership Inference Attacks—0
Distilling Vision-Language Foundation Models: A Data-Free Approach via Prompt Diversification—0
SeqMIA: Sequential-Metric Based Membership Inference AttackCode0
Teach Harder, Learn Poorer: Rethinking Hard Sample Distillation for GNN-to-MLP Knowledge DistillationCode0
Compact Language Models via Pruning and Knowledge DistillationCode3
Continual Panoptic Perception: Towards Multi-modal Incremental Interpretation of Remote Sensing ImagesCode0
ESP-MedSAM: Efficient Self-Prompting SAM for Universal Domain-Generalized Medical Image SegmentationCode2
Knowledge Distillation Approaches for Accurate and Efficient Recommender SystemCode1
Continual Distillation Learning: Knowledge Distillation in Prompt-based Continual Learning—0
DFMSD: Dual Feature Masking Stage-wise Knowledge Distillation for Object Detection—0
QuIIL at T3 challenge: Towards Automation in Life-Saving Intervention Procedures from First-Person ViewCode0
Open Vocabulary 3D Scene Understanding via Geometry Guided Self-Distillation—0
Make a Strong Teacher with Label Assistance: A Novel Knowledge Distillation Approach for Semantic SegmentationCode0
Discovery of novel antimicrobial peptides with notable antibacterial potency by a LLM-based foundation model—0
Exploring Deeper! Segment Anything Model with Depth Perception for Camouflaged Object DetectionCode1
Bridge Past and Future: Overcoming Information Asymmetry in Incremental Object DetectionCode1
Learning Modality-agnostic Representation for Semantic Segmentation from Any Modalities—0
MapDistill: Boosting Efficient Camera-based HD Map Construction via Camera-LiDAR Fusion Model Distillation—0
Mitigating Background Shift in Class-Incremental Semantic SegmentationCode1
Progressive Pretext Task Learning for Human Trajectory PredictionCode2
Relational Representation DistillationCode1
Discriminative and Consistent Representation DistillationCode1
Don't Throw Away Data: Better Sequence Knowledge Distillation—0
Leave No Knowledge Behind During Knowledge Distillation: Towards Practical and Effective Knowledge Distillation for Code-Switching ASR Using Realistic Data—0
Accessing Vision Foundation Models at ImageNet-level CostsCode2
Multi-Granularity Semantic Revision for Large Language Model Distillation—0
Enhancing Weakly-Supervised Histopathology Image Segmentation with Knowledge Distillation on MIL-Based Pseudo-LabelsCode0
LabelDistill: Label-guided Cross-modal Knowledge Distillation for Camera-based 3D Object DetectionCode1
Minimizing PLM-Based Few-Shot Intent DetectorsCode0
Background Adaptation with Residual Modeling for Exemplar-Free Class-Incremental Semantic Segmentation—0
A Survey on Symbolic Knowledge Distillation of Large Language Models—0
Uplifting Range-View-based 3D Semantic Segmentation in Real-Time with Multi-Sensor Fusion—0
BKDSNN: Enhancing the Performance of Learning-based Spiking Neural Networks Training with Blurred Knowledge DistillationCode1
SlideGCD: Slide-based Graph Collaborative Training with Knowledge Distillation for Whole Slide Image ClassificationCode0
3M-Health: Multimodal Multi-Teacher Knowledge Distillation for Mental Health DetectionCode0
From Easy to Hard: Learning Curricular Shape-aware Features for Robust Panoptic Scene Graph Generation—0
Adaptive Deep Iris Feature Extractor at Arbitrary Resolutions—0
Knowledge distillation to effectively attain both region-of-interest and global semantics from an image where multiple objects appearCode0
LokiLM: Technical Report—0
HDKD: Hybrid Data-Efficient Knowledge Distillation Network for Medical Image ClassificationCode0
A Guide To Effectively Leveraging LLMs for Low-Resource Text Summarization: Data Augmentation and Semi-supervised Approaches—0
Show:102550
← PrevPage 18 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