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 2451–2500 of 4240 papers

TitleStatusHype
Pro-KD: Progressive Distillation by Following the Footsteps of the Teacher—0
Promoting CNNs with Cross-Architecture Knowledge Distillation for Efficient Monocular Depth Estimation—0
PromptDet: A Lightweight 3D Object Detection Framework with LiDAR Prompts—0
Prompting to Distill: Boosting Data-Free Knowledge Distillation via Reinforced Prompt—0
Propagate & Distill: Towards Effective Graph Learners Using Propagation-Embracing MLPs—0
Prototypical Contrastive Predictive Coding—0
ProxylessKD: Direct Knowledge Distillation with Inherited Classifier for Face Recognition—0
Pseudo Knowledge Distillation: Towards Learning Optimal Instance-specific Label Smoothing Regularization—0
Pseudo-label Correction for Instance-dependent Noise Using Teacher-student Framework—0
Pseudo-Label Training and Model Inertia in Neural Machine Translation—0
Pseudo Supervised Monocular Depth Estimation with Teacher-Student Network—0
PTMs-TSCIL Pre-Trained Models Based Class-Incremental Learning—0
PURSUhInT: In Search of Informative Hint Points Based on Layer Clustering for Knowledge Distillation—0
In-Distribution Consistency Regularization Improves the Generalization of Quantization-Aware Training—0
Puzzle: Distillation-Based NAS for Inference-Optimized LLMs—0
QABISAR: Query-Article Bipartite Interactions for Statutory Article Retrieval—0
QA-HFL: Quality-Aware Hierarchical Federated Learning for Resource-Constrained Mobile Devices with Heterogeneous Image Quality—0
QCRD: Quality-guided Contrastive Rationale Distillation for Large Language Models—0
QKD: Quantization-aware Knowledge Distillation—0
QTI Submission to DCASE 2021: residual normalization for device-imbalanced acoustic scene classification with efficient design—0
QuaLA-MiniLM: a Quantized Length Adaptive MiniLM—0
Quantifying Knowledge Distillation Using Partial Information Decomposition—0
Quantifying the Knowledge in a DNN to Explain Knowledge Distillation for Classification—0
Quantized Feature Distillation for Network Quantization—0
Query-Based Knowledge Sharing for Open-Vocabulary Multi-Label Classification—0
Query Distillation: BERT-based Distillation for Ensemble Ranking—0
Query Optimization for Parametric Knowledge Refinement in Retrieval-Augmented Large Language Models—0
Quick Dense Retrievers Consume KALE: Post Training Kullback Leibler Alignment of Embeddings for Asymmetrical dual encoders—0
QUILL: Query Intent with Large Language Models using Retrieval Augmentation and Multi-stage Distillation—0
QuPeD: Quantized Personalization via Distillation with Applications to Federated Learning—0
Radio2Text: Streaming Speech Recognition Using mmWave Radio Signals—0
RadOcc: Learning Cross-Modality Occupancy Knowledge through Rendering Assisted Distillation—0
RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation—0
Random Conditioning for Diffusion Model Compression with Distillation—0
Random Conditioning with Distillation for Data-Efficient Diffusion Model Compression—0
Random Copolymer inverse design system orienting on Accurate discovering of Antimicrobial peptide-mimetic copolymers—0
RangeAugment: Efficient Online Augmentation with Range Learning—0
RankByGene: Gene-Guided Histopathology Representation Learning Through Cross-Modal Ranking Consistency—0
RankDistil: Knowledge Distillation for Ranking—0
RankDVQA-mini: Knowledge Distillation-Driven Deep Video Quality Assessment—0
Ranking-aware Continual Learning for LiDAR Place Recognition—0
MotherNets: Rapid Deep Ensemble Learning—0
Rationalization Models for Text-to-SQL—0
RAVIR: A Dataset and Methodology for the Semantic Segmentation and Quantitative Analysis of Retinal Arteries and Veins in Infrared Reflectance Imaging—0
RAWtoBit: A Fully End-to-end Camera ISP Network—0
RCKD: Response-Based Cross-Task Knowledge Distillation for Pathological Image Analysis—0
Lightweight Embedded FPGA Deployment of Learned Image Compression with Knowledge Distillation and Hybrid Quantization—0
RdimKD: Generic Distillation Paradigm by Dimensionality Reduction—0
Re2G: Retrieve, Rerank, Generate—0
Real-time Monocular Depth Estimation with Sparse Supervision on Mobile—0
Show:102550
← PrevPage 50 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