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 2651–2700 of 4240 papers

TitleStatusHype
Extreme compression of sentence-transformer ranker models: faster inference, longer battery life, and less storage on edge devices—0
Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?Code1
Knowledge Distillation of Transformer-based Language Models Revisited—0
QTI Submission to DCASE 2021: residual normalization for device-imbalanced acoustic scene classification with efficient design—0
Cooperative Retriever and Ranker in Deep RecommendersCode0
Revisiting Architecture-aware Knowledge Distillation: Smaller Models and Faster Search—0
Representative Teacher Keys for Knowledge Distillation Model Compression Based on Attention Mechanism for Image Classification—0
Feature Representation Learning for Robust Retinal Disease Detection from Optical Coherence Tomography ImagesCode0
Mixed Sample Augmentation for Online Distillation—0
Knowledge Distillation via Weighted Ensemble of Teaching Assistants—0
Conformer with dual-mode chunked attention for joint online and offline ASR—0
Knowledge Distillation for Oriented Object Detection on Aerial Images—0
MetaFed: Federated Learning among Federations with Cyclic Knowledge Distillation for Personalized HealthcareCode2
Revisiting Self-Distillation—0
Multi scale Feature Extraction and Fusion for Online Knowledge Distillation—0
FreeKD: Free-direction Knowledge Distillation for Graph Neural Networks—0
FreeTransfer-X: Safe and Label-Free Cross-Lingual Transfer from Off-the-Shelf Models—0
Toward Student-Oriented Teacher Network Training For Knowledge Distillation—0
Robust Distillation for Worst-class Performance—0
Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge DistillationCode0
Federated Bayesian Neural Regression: A Scalable Global Federated Gaussian Process—0
The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge DistillationCode1
Reducing Capacity Gap in Knowledge Distillation with Review Mechanism for Crowd CountingCode0
Knowledge Distillation Decision Tree for Unravelling Black-box Machine Learning Models—0
SDQ: Stochastic Differentiable Quantization with Mixed Precision—0
Narrowing the Coordinate-frame Gap in Behavior Prediction Models: Distillation for Efficient and Accurate Scene-centric Motion Forecasting—0
Reconsidering Learning Objectives in Unbiased Recommendation with Unobserved Confounders—0
cViL: Cross-Lingual Training of Vision-Language Models using Knowledge DistillationCode0
Confidence-aware Self-Semantic Distillation on Knowledge Graph Embedding—0
Self-Knowledge Distillation based Self-Supervised Learning for Covid-19 Detection from Chest X-Ray Images—0
Evaluation-oriented Knowledge Distillation for Deep Face Recognition—0
Lip-Listening: Mixing Senses to Understand Lips using Cross Modality Knowledge Distillation for Word-Based Models—0
Point-to-Voxel Knowledge Distillation for LiDAR Semantic SegmentationCode0
Vanilla Feature Distillation for Improving the Accuracy-Robustness Trade-Off in Adversarial Training—0
Guided Deep Metric Learning—0
Extreme Compression for Pre-trained Transformers Made Simple and Efficient—0
ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale TransformersCode2
3D-Augmented Contrastive Knowledge Distillation for Image-based Object Pose Estimation—0
Detecting Optimism in Tweets using Knowledge Distillation and Linguistic Analysis of Optimism—0
ORC: Network Group-based Knowledge Distillation using Online Role ChangeCode0
Generalized Supervised Contrastive Learning—0
Searching for COMETINHO: The Little Metric That Could—0
VFed-SSD: Towards Practical Vertical Federated Advertising—0
What Knowledge Gets Distilled in Knowledge Distillation?—0
itKD: Interchange Transfer-based Knowledge Distillation for 3D Object DetectionCode1
Knowledge Distillation for 6D Pose Estimation by Aligning Distributions of Local Predictions—0
RLx2: Training a Sparse Deep Reinforcement Learning Model from ScratchCode1
Spectral Maps for Learning on Subgraphs—0
Towards Efficient 3D Object Detection with Knowledge DistillationCode1
A General Multiple Data Augmentation Based Framework for Training Deep Neural Networks—0
Show:102550
← PrevPage 54 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