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 2851–2900 of 4240 papers

TitleStatusHype
SC2 Benchmark: Supervised Compression for Split Computing—0
Graph Flow: Cross-layer Graph Flow Distillation for Dual Efficient Medical Image SegmentationCode1
Unified Visual Transformer CompressionCode1
SATS: Self-Attention Transfer for Continual Semantic SegmentationCode1
On the benefits of knowledge distillation for adversarial robustness—0
DS3-Net: Difficulty-perceived Common-to-T1ce Semi-Supervised Multimodal MRI Synthesis Network—0
CEKD:Cross Ensemble Knowledge Distillation for Augmented Fine-grained Data—0
CMKD: CNN/Transformer-Based Cross-Model Knowledge Distillation for Audio ClassificationCode3
Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation—0
Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation—0
Medical Image Segmentation on MRI Images with Missing Modalities: A Review—0
Deep Class Incremental Learning from Decentralized DataCode0
Improving Neural ODEs via Knowledge Distillation—0
Look Backward and Forward: Self-Knowledge Distillation with Bidirectional Decoder for Neural Machine Translation—0
Model-Architecture Co-Design for High Performance Temporal GNN Inference on FPGACode0
Prediction-Guided Distillation for Dense Object DetectionCode1
Membership Privacy Protection for Image Translation Models via Adversarial Knowledge Distillation—0
Representation Compensation Networks for Continual Semantic SegmentationCode1
Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better TransferabilityCode1
Efficient Sub-structured Knowledge DistillationCode0
How many Observations are Enough? Knowledge Distillation for Trajectory Forecasting—0
PyNET-QxQ: An Efficient PyNET Variant for QxQ Bayer Pattern Demosaicing in CMOS Image SensorsCode0
On Generalizing Beyond Domains in Cross-Domain Continual Learning—0
Multi-trial Neural Architecture Search with Lottery Tickets—0
Overcoming Catastrophic Forgetting beyond Continual Learning: Balanced Training for Neural Machine TranslationCode1
Student Becomes Decathlon Master in Retinal Vessel Segmentation via Dual-teacher Multi-target Domain AdaptationCode0
Enhance Language Identification using Dual-mode Model with Knowledge DistillationCode0
Ensemble Knowledge Guided Sub-network Search and Fine-tuning for Filter PruningCode1
Consistent Representation Learning for Continual Relation ExtractionCode1
Better Supervisory Signals by Observing Learning PathsCode0
MIAShield: Defending Membership Inference Attacks via Preemptive Exclusion of Members—0
X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense CaptioningCode1
TRILLsson: Distilled Universal Paralinguistic Speech Representations—0
Dual Embodied-Symbolic Concept Representations for Deep Learning—0
Self-Supervised Vision Transformers Learn Visual Concepts in HistopathologyCode1
Confidence Based Bidirectional Global Context Aware Training Framework for Neural Machine Translation—0
TransKD: Transformer Knowledge Distillation for Efficient Semantic SegmentationCode1
Content-Variant Reference Image Quality Assessment via Knowledge DistillationCode1
Joint Answering and Explanation for Visual Commonsense ReasoningCode0
Bridging the Gap Between Patient-specific and Patient-independent Seizure Prediction via Knowledge Distillation—0
Learn From the Past: Experience Ensemble Knowledge Distillation—0
Efficient Video Segmentation Models with Per-frame Inference—0
Are All Linear Regions Created Equal?Code0
Multi-Teacher Knowledge Distillation for Incremental Implicitly-Refined Classification—0
Distilled Neural Networks for Efficient Learning to RankCode0
A Novel Architecture Slimming Method for Network Pruning and Knowledge Distillation—0
Learning Bayesian Sparse Networks with Full Experience Replay for Continual Learning—0
CaMEL: Mean Teacher Learning for Image CaptioningCode1
Cross-Task Knowledge Distillation in Multi-Task Recommendation—0
General Cyclical Training of Neural NetworksCode1
Show:102550
← PrevPage 58 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