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 2351–2400 of 4240 papers

TitleStatusHype
FEED: Feature-level Ensemble for Knowledge Distillation—0
Few-shot 3D LiDAR Semantic Segmentation for Autonomous Driving—0
Few-shot Face Image Translation via GAN Prior Distillation—0
Few-shot learning of neural networks from scratch by pseudo example optimization—0
Few-Shot Object Detection by Knowledge Distillation Using Bag-of-Visual-Words Representations—0
Optimizing Vision Transformers with Data-Free Knowledge Transfer—0
Optimizing YOLOv5s Object Detection through Knowledge Distillation algorithm—0
Oracle Teacher: Leveraging Target Information for Better Knowledge Distillation of CTC Models—0
Orderly Dual-Teacher Knowledge Distillation for Lightweight Human Pose Estimation—0
ORQA: A Benchmark and Foundation Model for Holistic Operating Room Modeling—0
Overcoming Language Priors for Visual Question Answering Based on Knowledge Distillation—0
P4: Towards private, personalized, and Peer-to-Peer learning—0
Pacemaker: Intermediate Teacher Knowledge Distillation For On-The-Fly Convolutional Neural Network—0
PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval—0
Pan-infection Foundation Framework Enables Multiple Pathogen Prediction—0
PANLP at MEDIQA 2019: Pre-trained Language Models, Transfer Learning and Knowledge Distillation—0
Papago’s Submission for the WMT21 Quality Estimation Shared Task—0
Paralinguistic Privacy Protection at the Edge—0
Parameter-Efficient and Student-Friendly Knowledge Distillation—0
Parameter-Efficient Conformers via Sharing Sparsely-Gated Experts for End-to-End Speech Recognition—0
Parameter Efficient Diverse Paraphrase Generation Using Sequence-Level Knowledge Distillation—0
Partial Knowledge Distillation for Alleviating the Inherent Inter-Class Discrepancy in Federated Learning—0
Partial to Whole Knowledge Distillation: Progressive Distilling Decomposed Knowledge Boosts Student Better—0
PC-LoRA: Low-Rank Adaptation for Progressive Model Compression with Knowledge Distillation—0
PDALN: Progressive Domain Adaptation over a Pre-trained Model for Low-Resource Cross-Domain Named Entity Recognition—0
Peak-Controlled Logits Poisoning Attack in Federated Distillation—0
Pea-KD: Parameter-efficient and Accurate Knowledge Distillation on BERT—0
Pea-KD: Parameter-efficient and accurate Knowledge Distillation—0
Peak-First CTC: Reducing the Peak Latency of CTC Models by Applying Peak-First Regularization—0
Peer Collaborative Learning for Polyphonic Sound Event Detection—0
Learning to Maximize Speech Quality Directly Using MOS Prediction for Neural Text-to-Speech—0
Performance-Aware Mutual Knowledge Distillation for Improving Neural Architecture Search—0
Performance-Efficiency Trade-Offs in Adapting Language Models to Text Classification Tasks—0
Performance-Guided LLM Knowledge Distillation for Efficient Text Classification at Scale—0
Periocular Embedding Learning with Consistent Knowledge Distillation from Face—0
Personalised Federated Learning: A Combinational Approach—0
Personalized Decentralized Federated Learning with Knowledge Distillation—0
PGX: A Multi-level GNN Explanation Framework Based on Separate Knowledge Distillation Processes—0
PHI-S: Distribution Balancing for Label-Free Multi-Teacher Distillation—0
PicoSAM2: Low-Latency Segmentation In-Sensor for Edge Vision Applications—0
PILE: Pairwise Iterative Logits Ensemble for Multi-Teacher Labeled Distillation—0
PIRB: A Comprehensive Benchmark of Polish Dense and Hybrid Text Retrieval Methods—0
PISCO: Pretty Simple Compression for Retrieval-Augmented Generation—0
Pixel Invisibility: Detecting Objects Invisible in Color Images—0
P-KDGAN: Progressive Knowledge Distillation with GANs for One-class Novelty Detection—0
PKD: General Distillation Framework for Object Detectors via Pearson Correlation Coefficient—0
PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs—0
PlaStIL: Plastic and Stable Memory-Free Class-Incremental Learning—0
Plug-and-Play Interpretable Responsible Text-to-Image Generation via Dual-Space Multi-facet Concept Control—0
Point Adversarial Self Mining: A Simple Method for Facial Expression Recognition—0
Show:102550
← PrevPage 48 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