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 651–700 of 4240 papers

TitleStatusHype
Consistent Representation Learning for Continual Relation ExtractionCode1
Ensemble Knowledge Guided Sub-network Search and Fine-tuning for Filter PruningCode1
X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense CaptioningCode1
Self-Supervised Vision Transformers Learn Visual Concepts in HistopathologyCode1
TransKD: Transformer Knowledge Distillation for Efficient Semantic SegmentationCode1
Content-Variant Reference Image Quality Assessment via Knowledge DistillationCode1
CaMEL: Mean Teacher Learning for Image CaptioningCode1
General Cyclical Training of Neural NetworksCode1
ZeroGen: Efficient Zero-shot Learning via Dataset GenerationCode1
FAMIE: A Fast Active Learning Framework for Multilingual Information ExtractionCode1
Point-Level Region Contrast for Object Detection Pre-TrainingCode1
Exploring Inter-Channel Correlation for Diversity-preserved KnowledgeDistillationCode1
Local Feature Matching with Transformers for low-end devicesCode1
Global-Reasoned Multi-Task Learning Model for Surgical Scene UnderstandingCode1
It's All in the Head: Representation Knowledge Distillation through Classifier SharingCode1
SimReg: Regression as a Simple Yet Effective Tool for Self-supervised Knowledge DistillationCode1
Robust and Resource-Efficient Data-Free Knowledge Distillation by Generative Pseudo ReplayCode1
Role of Data Augmentation Strategies in Knowledge Distillation for Wearable Sensor DataCode1
Learn From Others and Be Yourself in Heterogeneous Federated LearningCode1
Confidence-Aware Multi-Teacher Knowledge DistillationCode1
Deep Graph-level Anomaly Detection by Glocal Knowledge DistillationCode1
Pixel Distillation: A New Knowledge Distillation Scheme for Low-Resolution Image RecognitionCode1
Data Efficient Language-supervised Zero-shot Recognition with Optimal Transport DistillationCode1
Learning Cross-Lingual IR from an English RetrieverCode1
A Deep Knowledge Distillation framework for EEG assisted enhancement of single-lead ECG based sleep stagingCode1
Up to 100 Faster Data-free Knowledge DistillationCode1
DistilCSE: Effective Knowledge Distillation For Contrastive Sentence EmbeddingsCode1
Mask-invariant Face Recognition through Template-level Knowledge DistillationCode1
Improving Neural Cross-Lingual Summarization via Employing Optimal Transport Distance for Knowledge DistillationCode1
A Contrastive Distillation Approach for Incremental Semantic Segmentation in Aerial ImagesCode1
Tiny-NewsRec: Effective and Efficient PLM-based News RecommendationCode1
A Fast Knowledge Distillation Framework for Visual RecognitionCode1
Information Theoretic Representation DistillationCode1
Aligned Structured Sparsity Learning for Efficient Image Super-ResolutionCode1
Slow Learning and Fast Inference: Efficient Graph Similarity Computation via Knowledge DistillationCode1
Distilling Meta Knowledge on Heterogeneous Graph for Illicit Drug Trafficker Detection on Social MediaCode1
Comprehensive Knowledge Distillation with Causal InterventionCode1
The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single ImageCode1
WiFi-based Multi-task SensingCode1
Self-slimmed Vision TransformerCode1
EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge DistillationCode1
Focal and Global Knowledge Distillation for DetectorsCode1
On Representation Knowledge Distillation for Graph Neural NetworksCode1
Distilling Object Detectors with Feature RichnessCode1
Learning Distilled Collaboration Graph for Multi-Agent PerceptionCode1
Mosaicking to Distill: Knowledge Distillation from Out-of-Domain DataCode1
Instance-Conditional Knowledge Distillation for Object DetectionCode1
Anti-Distillation Backdoor Attacks: Backdoors Can Really Survive in Knowledge DistillationCode1
Pixel-by-Pixel Cross-Domain Alignment for Few-Shot Semantic SegmentationCode1
Graph-less Neural Networks: Teaching Old MLPs New Tricks via DistillationCode1
Show:102550
← PrevPage 14 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