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 2101–2150 of 4240 papers

TitleStatusHype
MetaMixer: A Regularization Strategy for Online Knowledge Distillation—0
Teacher-Student Knowledge Distillation for Radar Perception on Embedded Accelerators—0
SCPNet: Semantic Scene Completion on Point CloudCode1
Continuous sign language recognition based on cross-resolution knowledge distillation—0
Visual-Policy Learning through Multi-Camera View to Single-Camera View Knowledge Distillation for Robot Manipulation Tasks—0
Extending global-local view alignment for self-supervised learning with remote sensing imageryCode1
Knowledge Distillation for Efficient Sequences of Training Runs—0
Digital Twin-Assisted Knowledge Distillation Framework for Heterogeneous Federated Learning—0
Robust Knowledge Distillation from RNN-T Models With Noisy Training Labels Using Full-Sum Loss—0
FedACK: Federated Adversarial Contrastive Knowledge Distillation for Cross-Lingual and Cross-Model Social Bot DetectionCode1
Dynamic Y-KD: A Hybrid Approach to Continual Instance Segmentation—0
Learning the Wrong Lessons: Inserting Trojans During Knowledge Distillation—0
NIFF: Alleviating Forgetting in Generalized Few-Shot Object Detection via Neural Instance Feature Forging—0
Enhancing Low-resolution Face Recognition with Feature Similarity Knowledge DistillationCode1
PreFallKD: Pre-Impact Fall Detection via CNN-ViT Knowledge DistillationCode0
Gradient-Guided Knowledge Distillation for Object Detectors—0
Adaptive Knowledge Distillation between Text and Speech Pre-trained Models—0
Students Parrot Their Teachers: Membership Inference on Model Distillation—0
KDSM: An uplift modeling framework based on knowledge distillation and sample matching—0
IKD+: Reliable Low Complexity Deep Models For Retinopathy Classification—0
DistilPose: Tokenized Pose Regression with Heatmap DistillationCode1
Pre-trained Model Representations and their Robustness against Noise for Speech Emotion Analysis—0
Unsupervised Deep Digital Staining For Microscopic Cell Images Via Knowledge Distillation—0
X^3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detection—0
Weakly-supervised HOI Detection via Prior-guided Bi-level Representation Learning—0
Distillation from Heterogeneous Models for Top-K RecommendationCode1
Towards Activated Muscle Group Estimation in the WildCode1
Distilling Multi-Level X-vector Knowledge for Small-footprint Speaker Verification—0
Letz Translate: Low-Resource Machine Translation for Luxembourgish—0
Backdoor for Debias: Mitigating Model Bias with Backdoor Attack-based Artificial BiasCode0
Distilled Reverse Attention Network for Open-world Compositional Zero-Shot Learning—0
Towards domain generalisation in ASR with elitist sampling and ensemble knowledge distillation—0
Language-Universal Adapter Learning with Knowledge Distillation for End-to-End Multilingual Speech RecognitionCode0
Incremental Learning of Acoustic Scenes and Sound Events—0
Learning to Retain while Acquiring: Combating Distribution-Shift in Adversarial Data-Free Knowledge Distillation—0
Generic-to-Specific Distillation of Masked AutoencodersCode1
Leveraging Angular Distributions for Improved Knowledge Distillation—0
Graph-based Knowledge Distillation: A survey and experimental evaluationCode1
OccDepth: A Depth-Aware Method for 3D Semantic Scene CompletionCode2
A Light-weight Deep Learning Model for Remote Sensing Image Classification—0
Ensemble knowledge distillation of self-supervised speech models—0
A Knowledge Distillation framework for Multi-Organ Segmentation of Medaka Fish in Tomographic Image—0
Practical Knowledge Distillation: Using DNNs to Beat DNNs—0
Exploring Social Media for Early Detection of Depression in COVID-19 PatientsCode0
Personalized Decentralized Federated Learning with Knowledge Distillation—0
A framework for benchmarking class-out-of-distribution detection and its application to ImageNetCode1
Teacher Intervention: Improving Convergence of Quantization Aware Training for Ultra-Low Precision TransformersCode0
A Neural Span-Based Continual Named Entity Recognition ModelCode1
CEKD: Cross-Modal Edge-Privileged Knowledge Distillation for Semantic Scene Understanding Using Only Thermal ImagesCode1
Distilling Calibrated Student from an Uncalibrated Teacher—0
Show:102550
← PrevPage 43 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