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
Knowledge Distillation from Cross Teaching Teachers for Efficient Semi-Supervised Abdominal Organ Segmentation in CTCode0
PILE: Pairwise Iterative Logits Ensemble for Multi-Teacher Labeled Distillation—0
FAN-Trans: Online Knowledge Distillation for Facial Action Unit Detection—0
Knowledge Distillation for Federated Learning: a Practical Guide—0
Bridging Fairness and Environmental Sustainability in Natural Language Processing—0
Understanding the Role of Mixup in Knowledge Distillation: An Empirical StudyCode0
Peak-First CTC: Reducing the Peak Latency of CTC Models by Applying Peak-First Regularization—0
Closing the Gap between Client and Global Model Performance in Heterogeneous Federated Learning—0
Breaking the trade-off in personalized speech enhancement with cross-task knowledge distillation—0
LightVessel: Exploring Lightweight Coronary Artery Vessel Segmentation via Similarity Knowledge Distillation—0
Multi-level Distillation of Semantic Knowledge for Pre-training Multilingual Language Model—0
Gradient Knowledge Distillation for Pre-trained Language ModelsCode0
ARDIR: Improving Robustness using Knowledge Distillation of Internal Representation—0
Fairness without Demographics through Knowledge DistillationCode0
Lightweight Sound Event Detection Model with RepVGG Architecture—0
Enhancing Chinese Multi-Label Text Classification Performance with Response-based Knowledge Distillation—0
Maximum Likelihood Distillation for Robust Modulation Classification—0
Predicting Multi-Codebook Vector Quantization Indexes for Knowledge Distillation—0
Lightweight Neural Network with Knowledge Distillation for CSI Feedback—0
Generative Negative Text Replay for Continual Vision-Language Pretraining—0
QuaLA-MiniLM: a Quantized Length Adaptive MiniLM—0
Application of Knowledge Distillation to Multi-task Speech Representation Learning—0
Completely Heterogeneous Federated Learning—0
Teacher-Student Architecture for Knowledge Learning: A Survey—0
Can Current Explainability Help Provide References in Clinical Notes to Support Humans Annotate Medical Codes?—0
BEBERT: Efficient and Robust Binary Ensemble BERTCode0
Semi-UFormer: Semi-supervised Uncertainty-aware Transformer for Image Dehazing—0
Li3DeTr: A LiDAR based 3D Detection Transformer—0
Weight Averaging: A Simple Yet Effective Method to Overcome Catastrophic Forgetting in Automatic Speech Recognition—0
Collaborative Multi-Teacher Knowledge Distillation for Learning Low Bit-width Deep Neural Networks—0
Fast DistilBERT on CPUs—0
QUILL: Query Intent with Large Language Models using Retrieval Augmentation and Multi-stage Distillation—0
Long-tailed Food Classification—0
Online Cross-Layer Knowledge Distillation on Graph Neural Networks with Deep Supervision—0
An Effective Deep Network for Head Pose Estimation without Keypoints—0
Referee: Reference-Free Sentence Summarization with Sharper Controllability through Symbolic Knowledge Distillation—0
Legal-Tech Open Diaries: Lesson learned on how to develop and deploy light-weight models in the era of humongous Language Models—0
Respecting Transfer Gap in Knowledge Distillation—0
Adaptive Label Smoothing with Self-Knowledge in Natural Language Generation—0
Hard Gate Knowledge Distillation -- Leverage Calibration for Robust and Reliable Language Model—0
Performance-Efficiency Trade-Offs in Adapting Language Models to Text Classification Tasks—0
Augmentation with Projection: Towards an Effective and Efficient Data Augmentation Paradigm for Distillation—0
Modeling Document-level Temporal Structures for Building Temporal Dependency GraphsCode0
Distilling the Undistillable: Learning from a Nasty TeacherCode0
Semi-supervised object detection based on single-stage detector for thighbone fracture localization—0
Toward Multiple Specialty Learners for Explaining GNNs via Online Knowledge Distillation—0
Similarity of Neural Architectures using Adversarial Attack Transferability—0
ADPS: Asymmetric Distillation Post-Segmentation for Image Anomaly Detection—0
A baseline revisited: Pushing the limits of multi-segment models for context-aware translation—0
On effects of Knowledge Distillation on Transfer Learning—0
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