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 551–600 of 4240 papers

TitleStatusHype
Decomposed Knowledge Distillation for Class-Incremental Semantic SegmentationCode1
Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational AgentsCode1
Categorical Relation-Preserving Contrastive Knowledge Distillation for Medical Image ClassificationCode1
Dice Semimetric Losses: Optimizing the Dice Score with Soft LabelsCode1
Anti-Distillation Backdoor Attacks: Backdoors Can Really Survive in Knowledge DistillationCode1
DiGA: Distil to Generalize and then Adapt for Domain Adaptive Semantic SegmentationCode1
Extending global-local view alignment for self-supervised learning with remote sensing imageryCode1
DIOD: Self-Distillation Meets Object DiscoveryCode1
DA-Mamba: Domain Adaptive Hybrid Mamba-Transformer Based One-Stage Object DetectionCode1
CCL: Continual Contrastive Learning for LiDAR Place RecognitionCode1
CLIP-KD: An Empirical Study of CLIP Model DistillationCode1
CLIP model is an Efficient Continual LearnerCode1
Class-relation Knowledge Distillation for Novel Class DiscoveryCode1
Distilling Knowledge from Graph Convolutional NetworksCode1
CEKD: Cross-Modal Edge-Privileged Knowledge Distillation for Semantic Scene Understanding Using Only Thermal ImagesCode1
CEN-HDR: Computationally Efficient neural Network for real-time High Dynamic Range imagingCode1
Tracking-by-Trackers with a Distilled and Reinforced ModelCode1
Distillation Matters: Empowering Sequential Recommenders to Match the Performance of Large Language ModelCode1
DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge DistillationCode1
Channel-Aware Distillation Transformer for Depth Estimation on Nano DronesCode1
Channel Distillation: Channel-Wise Attention for Knowledge DistillationCode1
Distilling a Powerful Student Model via Online Knowledge DistillationCode1
Channel Gating Neural NetworksCode1
Distilling Autoregressive Models to Obtain High-Performance Non-Autoregressive Solvers for Vehicle Routing Problems with Faster Inference SpeedCode1
Data-Free Network Quantization With Adversarial Knowledge DistillationCode1
Channel-wise Knowledge Distillation for Dense PredictionCode1
Distilling Knowledge from Reader to Retriever for Question AnsweringCode1
CheXseg: Combining Expert Annotations with DNN-generated Saliency Maps for X-ray SegmentationCode1
Chinese grammatical error correction based on knowledge distillationCode1
Distilling Knowledge via Intermediate ClassifiersCode1
Circumventing Outliers of AutoAugment with Knowledge DistillationCode1
Distilling Large Vision-Language Model with Out-of-Distribution GeneralizabilityCode1
FocusNet: Classifying Better by Focusing on Confusing ClassesCode1
Distilling Object Detectors with Feature RichnessCode1
Distilling Script Knowledge from Large Language Models for Constrained Language PlanningCode1
Class Attention Transfer Based Knowledge DistillationCode1
Advancing Pre-trained Teacher: Towards Robust Feature Discrepancy for Anomaly DetectionCode1
Class-Balanced Distillation for Long-Tailed Visual RecognitionCode1
Decoupled Kullback-Leibler Divergence LossCode1
Distill on the Go: Online knowledge distillation in self-supervised learningCode1
Data-Free Knowledge Distillation for Heterogeneous Federated LearningCode1
Cloud Object Detector Adaptation by Integrating Different Source KnowledgeCode1
Advantage-Guided Distillation for Preference Alignment in Small Language ModelsCode1
DistilVPR: Cross-Modal Knowledge Distillation for Visual Place RecognitionCode1
3D Annotation-Free Learning by Distilling 2D Open-Vocabulary Segmentation Models for Autonomous DrivingCode1
Distributed Dynamic Map Fusion via Federated Learning for Intelligent Networked VehiclesCode1
Class-Incremental Learning by Knowledge Distillation with Adaptive Feature ConsolidationCode1
Distribution-aware Forgetting Compensation for Exemplar-Free Lifelong Person Re-identificationCode1
Are Intermediate Layers and Labels Really Necessary? A General Language Model Distillation MethodCode1
Data-Free Class-Incremental Hand Gesture RecognitionCode1
Show:102550
← PrevPage 12 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