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 1651–1700 of 4240 papers

TitleStatusHype
Facilitating NSFW Text Detection in Open-Domain Dialogue Systems via Knowledge DistillationCode0
Distilling HuBERT with LSTMs via Decoupled Knowledge Distillation—0
DFIL: Deepfake Incremental Learning by Exploiting Domain-invariant Forgery CluesCode1
Heterogeneous Generative Knowledge Distillation with Masked Image Modeling—0
FDCNet: Feature Drift Compensation Network for Class-Incremental Weakly Supervised Object LocalizationCode1
UNIDEAL: Curriculum Knowledge Distillation Federated Learning—0
One-Class Knowledge Distillation for Spoofing Speech Detection—0
Privacy-preserving Early Detection of Epileptic Seizures in VideosCode0
Cross-lingual Knowledge Distillation via Flow-based Voice Conversion for Robust Polyglot Text-To-Speech—0
Two-Step Knowledge Distillation for Tiny Speech Enhancement—0
Adaptive Prompt Learning with Distilled Connective Knowledge for Implicit Discourse Relation RecognitionCode0
ChromaDistill: Colorizing Monochrome Radiance Fields with Knowledge Distillation—0
CoLLD: Contrastive Layer-to-layer Distillation for Compressing Multilingual Pre-trained Speech Encoders—0
A Novel Local-Global Feature Fusion Framework for Body-weight Exercise Recognition with Pressure Mapping Sensors—0
Continual Learning with Dirichlet Generative-based Rehearsal—0
Self-Training and Multi-Task Learning for Limited Data: Evaluation Study on Object Detection—0
KD-FixMatch: Knowledge Distillation Siamese Neural Networks—0
DeViT: Decomposing Vision Transformers for Collaborative Inference in Edge Devices—0
DAD++: Improved Data-free Test Time Adversarial DefenseCode0
Exploiting CLIP for Zero-shot HOI Detection Requires Knowledge Distillation at Multiple LevelsCode0
Speech Emotion Recognition with Distilled Prosodic and Linguistic Affect Representations—0
Decoding visual brain representations from electroencephalography through Knowledge Distillation and latent diffusion modelsCode0
Knowledge Distillation-Empowered Digital Twin for Anomaly Detection—0
Towards Mitigating Architecture Overfitting on Distilled DatasetsCode0
3D Denoisers are Good 2D Teachers: Molecular Pretraining via Denoising and Cross-Modal Distillation—0
Towards Comparable Knowledge Distillation in Semantic Image Segmentation—0
Leveraging ASR Pretrained Conformers for Speaker Verification through Transfer Learning and Knowledge Distillation—0
Knowledge Distillation Layer that Lets the Student DecideCode0
DMKD: Improving Feature-based Knowledge Distillation for Object Detection Via Dual Masking Augmentation—0
Rethinking Momentum Knowledge Distillation in Online Continual LearningCode1
A deep Natural Language Inference predictor without language-specific training data—0
Fast and High-Performance Learned Image Compression With Improved Checkerboard Context Model, Deformable Residual Module, and Knowledge Distillation—0
TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models—0
Probabilistic Self-supervised Learning via Scoring Rules Minimization—0
A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking—0
On the Query Strategies for Efficient Online Active Distillation—0
Prior Knowledge Guided Network for Video Anomaly Detection—0
COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using TransformersCode1
Knowledge Distillation from Non-streaming to Streaming ASR Encoder using Auxiliary Non-streaming Layer—0
Adversarial Finetuning with Latent Representation Constraint to Mitigate Accuracy-Robustness Tradeoff—0
MoMA: Momentum Contrastive Learning with Multi-head Attention-based Knowledge Distillation for Histopathology Image AnalysisCode0
Towards Long-Tailed Recognition for Graph Classification via Collaborative Experts—0
Exploring Multi-Modal Contextual Knowledge for Open-Vocabulary Object Detection—0
SpikeBERT: A Language Spikformer Learned from BERT with Knowledge DistillationCode1
SynthDistill: Face Recognition with Knowledge Distillation from Synthetic DataCode0
Bridging Cross-task Protocol Inconsistency for Distillation in Dense Object DetectionCode1
Distilled GPT for Source Code SummarizationCode0
Boosting Residual Networks with Group KnowledgeCode0
DM-VTON: Distilled Mobile Real-time Virtual Try-OnCode1
Improving Knowledge Distillation for BERT Models: Loss Functions, Mapping Methods, and Weight Tuning—0
Show:102550
← PrevPage 34 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