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 1101–1150 of 4240 papers

TitleStatusHype
Retrieval-Oriented Knowledge for Click-Through Rate PredictionCode1
A Novel Spike Transformer Network for Depth Estimation from Event Cameras via Cross-modality Knowledge Distillation—0
Correlation-Decoupled Knowledge Distillation for Multimodal Sentiment Analysis with Incomplete Modalities—0
Promoting CNNs with Cross-Architecture Knowledge Distillation for Efficient Monocular Depth Estimation—0
BeSound: Bluetooth-Based Position Estimation Enhancing with Cross-Modality Distillation—0
Compressed Meta-Optical Encoder for Image Classification—0
Sentence-Level or Token-Level? A Comprehensive Study on Knowledge Distillation—0
Distributed Learning for Wi-Fi AP Load Prediction—0
Towards Multi-Morphology Controllers with Diversity and Knowledge DistillationCode0
DynaMMo: Dynamic Model Merging for Efficient Class Incremental Learning for Medical ImagesCode0
From LLM to NMT: Advancing Low-Resource Machine Translation with Claude—0
CKD: Contrastive Knowledge Distillation from A Sample-wise PerspectiveCode0
FedTAD: Topology-aware Data-free Knowledge Distillation for Subgraph Federated Learning—0
EncodeNet: A Framework for Boosting DNN Accuracy with Entropy-driven Generalized Converting Autoencoder—0
MergeNet: Knowledge Migration across Heterogeneous Models, Tasks, and Modalities—0
Dynamic Temperature Knowledge DistillationCode1
Parameter Efficient Diverse Paraphrase Generation Using Sequence-Level Knowledge Distillation—0
EdgeFusion: On-Device Text-to-Image Generation—0
Data-free Knowledge Distillation for Fine-grained Visual CategorizationCode0
KDk: A Defense Mechanism Against Label Inference Attacks in Vertical Federated Learning—0
LAPTOP-Diff: Layer Pruning and Normalized Distillation for Compressing Diffusion Models—0
GhostNetV3: Exploring the Training Strategies for Compact Models—0
A Progressive Framework of Vision-language Knowledge Distillation and Alignment for Multilingual Scene—0
Comprehensive Survey of Model Compression and Speed up for Vision Transformers—0
MK-SGN: A Spiking Graph Convolutional Network with Multimodal Fusion and Knowledge Distillation for Skeleton-based Action Recognition—0
Camera clustering for scalable stream-based active distillationCode1
Digging into contrastive learning for robust depth estimation with diffusion modelsCode1
ReffAKD: Resource-efficient Autoencoder-based Knowledge DistillationCode0
AI-KD: Towards Alignment Invariant Face Image Quality Assessment Using Knowledge DistillationCode0
MTKD: Multi-Teacher Knowledge Distillation for Image Super-Resolution—0
Weight Copy and Low-Rank Adaptation for Few-Shot Distillation of Vision TransformersCode0
Navigating the Landscape of Large Language Models: A Comprehensive Review and Analysis of Paradigms and Fine-Tuning StrategiesCode0
Edge-Efficient Deep Learning Models for Automatic Modulation Classification: A Performance Analysis—0
Adversarial Robustness of Distilled and Pruned Deep Learning-based Wireless Classifiers—0
Boosting Self-Supervision for Single-View Scene Completion via Knowledge Distillation—0
Rethinking Transformer-Based Blind-Spot Network for Self-Supervised Image DenoisingCode2
Remembering Transformer for Continual Learning—0
A predictive machine learning force field framework for liquid electrolyte development—0
Optimization Methods for Personalizing Large Language Models through Retrieval AugmentationCode2
Improving Facial Landmark Detection Accuracy and Efficiency with Knowledge Distillation—0
Robust feature knowledge distillation for enhanced performance of lightweight crack segmentation models—0
CLIP-Embed-KD: Computationally Efficient Knowledge Distillation Using Embeddings as TeachersCode1
GHOST: Grounded Human Motion Generation with Open Vocabulary Scene-and-Text Contexts—0
Bootstrapping Chest CT Image Understanding by Distilling Knowledge from X-ray Expert Models—0
MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object DetectionCode1
Diffusion Time-step Curriculum for One Image to 3D GenerationCode2
What Happens When Small Is Made Smaller? Exploring the Impact of Compression on Small Data Pretrained Language Models—0
Do We Really Need a Complex Agent System? Distill Embodied Agent into a Single Model—0
Knowledge Distillation-Based Model Extraction Attack using GAN-based Private Counterfactual ExplanationsCode0
On the Surprising Efficacy of Distillation as an Alternative to Pre-Training Small ModelsCode0
Show:102550
← PrevPage 23 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