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 2051–2100 of 4240 papers

TitleStatusHype
Empowering Dual-Encoder with Query Generator for Cross-Lingual Dense Retrieval—0
UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye ViewCode1
Mutually-paced Knowledge Distillation for Cross-lingual Temporal Knowledge Graph Reasoning—0
Generalization Matters: Loss Minima Flattening via Parameter Hybridization for Efficient Online Knowledge DistillationCode0
Preserving Linear Separability in Continual Learning by Backward Feature ProjectionCode1
Multi-Frame Self-Supervised Depth Estimation with Multi-Scale Feature Fusion in Dynamic Scenes—0
Multi-view knowledge distillation transformer for human action recognition—0
Dealing With Heterogeneous 3D MR Knee Images: A Federated Few-Shot Learning Method With Dual Knowledge DistillationCode0
Supervised Masked Knowledge Distillation for Few-Shot TransformersCode1
Task-Attentive Transformer Architecture for Continual Learning of Vision-and-Language Tasks Using Knowledge Distillation—0
DyLiN: Making Light Field Networks Dynamic—0
Mixed-Type Wafer Classification For Low Memory Devices Using Knowledge Distillation—0
Decoupled Multimodal Distilling for Emotion RecognitionCode1
Exploiting Unlabelled Photos for Stronger Fine-Grained SBIR—0
Edge-free but Structure-aware: Prototype-Guided Knowledge Distillation from GNNs to MLPs—0
CCL: Continual Contrastive Learning for LiDAR Place RecognitionCode1
From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels—0
Open-Vocabulary Object Detection using Pseudo Caption Labels—0
A Simple and Generic Framework for Feature Distillation via Channel-wise Transformation—0
From Wide to Deep: Dimension Lifting Network for Parameter-efficient Knowledge Graph Embedding—0
MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillationCode0
Heterogeneous-Branch Collaborative Learning for Dialogue Generation—0
Out of Thin Air: Exploring Data-Free Adversarial Robustness Distillation—0
Assessor-Guided Learning for Continual EnvironmentsCode0
Knowledge Distillation from Multiple Foundation Models for End-to-End Speech Recognition—0
Understanding the Role of the Projector in Knowledge DistillationCode1
More From Less: Self-Supervised Knowledge Distillation for Routine Histopathology Data—0
AdaptGuard: Defending Against Universal Attacks for Model AdaptationCode1
An Empirical Study of Pre-trained Language Models in Simple Knowledge Graph Question AnsweringCode0
DC-CCL: Device-Cloud Collaborative Controlled Learning for Large Vision Models—0
Crowd Counting with Online Knowledge Learning—0
Confidence Attention and Generalization Enhanced Distillation for Continuous Video Domain Adaptation—0
Whole-slide-imaging Cancer Metastases Detection and Localization with Limited Tumorous DataCode0
Channel-Aware Distillation Transformer for Depth Estimation on Nano DronesCode1
TeSLA: Test-Time Self-Learning With Automatic Adversarial AugmentationCode1
Prototype Knowledge Distillation for Medical Segmentation with Missing ModalityCode1
Distill n' Explain: explaining graph neural networks using simple surrogatesCode0
Action knowledge for video captioning with graph neural networksCode1
Neural Architecture Search for Effective Teacher-Student Knowledge Transfer in Language Models—0
Towards a Smaller Student: Capacity Dynamic Distillation for Efficient Image Retrieval—0
Global Knowledge Calibration for Fast Open-Vocabulary SegmentationCode1
Knowledge Distillation for Adaptive MRI Prostate Segmentation Based on Limit-Trained Multi-Teacher Models—0
DistillW2V2: A Small and Streaming Wav2vec 2.0 Based ASR Model—0
Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset ReinforcementCode1
Graph-less Collaborative FilteringCode1
Cross-resolution Face Recognition via Identity-Preserving Network and Knowledge Distillation—0
DualFair: Fair Representation Learning at Both Group and Individual Levels via Contrastive Self-supervisionCode1
Knowledge Distillation from Single to Multi Labels: an Empirical StudyCode0
Teacher-Student Knowledge Distillation for Radar Perception on Embedded Accelerators—0
MetaMixer: A Regularization Strategy for Online Knowledge Distillation—0
Show:102550
← PrevPage 42 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