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 1301–1350 of 4240 papers

TitleStatusHype
GraphKD: Exploring Knowledge Distillation Towards Document Object Detection with Structured Graph CreationCode1
On Good Practices for Task-Specific Distillation of Large Pretrained Visual Models—0
Knowledge Distillation Based on Transformed Teacher MatchingCode1
BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-DistillationCode4
Incremental Sequence Labeling: A Tale of Two ShiftsCode2
Cultural Commonsense Knowledge for Intercultural Dialogues—0
FedD2S: Personalized Data-Free Federated Knowledge Distillation—0
Distilled Gradual Pruning with Pruned Fine-tuningCode0
Walsh-domain Neural Network for Power Amplifier Behavioral Modelling and Digital Predistortion—0
Model Compression and Efficient Inference for Large Language Models: A Survey—0
NutePrune: Efficient Progressive Pruning with Numerous Teachers for Large Language ModelsCode0
Leveraging Large Language Models for Enhanced NLP Task Performance through Knowledge Distillation and Optimized Training Strategies—0
FedSiKD: Clients Similarity and Knowledge Distillation: Addressing Non-i.i.d. and Constraints in Federated LearningCode0
Integrating ChatGPT into Secure Hospital Networks: A Case Study on Improving Radiology Report Analysis—0
APALU: A Trainable, Adaptive Activation Function for Deep Learning Networks—0
Two-Stage Multi-task Self-Supervised Learning for Medical Image Segmentation—0
Training Heterogeneous Client Models using Knowledge Distillation in Serverless Federated LearningCode1
Domain Adaptable Fine-Tune Distillation Framework For Advancing Farm SurveillanceCode0
Embedding Compression for Teacher-to-Student Knowledge Transfer—0
Multi-source-free Domain Adaptation via Uncertainty-aware Adaptive DistillationCode0
Large Language Model Meets Graph Neural Network in Knowledge Distillation—0
Knowledge Distillation for Road Detection based on cross-model Semi-Supervised Learning—0
Beyond Answers: Transferring Reasoning Capabilities to Smaller LLMs Using Multi-Teacher Knowledge DistillationCode0
EfficientViT-SAM: Accelerated Segment Anything Model Without Accuracy Loss—0
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation ModelsCode1
DistiLLM: Towards Streamlined Distillation for Large Language ModelsCode3
A Survey on Transformer Compression—0
Large Language Model Distilling Medication Recommendation ModelCode1
BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge DistillationCode1
Dual Knowledge Distillation for Efficient Sound Event Detection—0
Good Teachers Explain: Explanation-Enhanced Knowledge DistillationCode1
LQER: Low-Rank Quantization Error Reconstruction for LLMsCode1
Cooperative Knowledge Distillation: A Learner Agnostic ApproachCode0
Bi-CryptoNets: Leveraging Different-Level Privacy for Encrypted Inference—0
Spiking CenterNet: A Distillation-boosted Spiking Neural Network for Object Detection—0
Class incremental learning with probability dampening and cascaded gated classifierCode0
Faster Inference of Integer SWIN Transformer by Removing the GELU Activation—0
Addressing Bias Through Ensemble Learning and Regularized Fine-Tuning—0
Dual-Student Knowledge Distillation Networks for Unsupervised Anomaly Detection—0
Augmenting Offline Reinforcement Learning with State-only Interactions—0
Scavenging Hyena: Distilling Transformers into Long Convolution Models—0
EPSD: Early Pruning with Self-Distillation for Efficient Model Compression—0
LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval and DistillationCode2
Stolen Subwords: Importance of Vocabularies for Machine Translation Model StealingCode0
TQCompressor: improving tensor decomposition methods in neural networks via permutationsCode0
Face to Cartoon Incremental Super-Resolution using Knowledge Distillation—0
Dynamic Transformer Architecture for Continual Learning of Multimodal Tasks—0
Distilling Privileged Multimodal Information for Expression Recognition using Optimal Transport—0
A Comprehensive Survey of Compression Algorithms for Language Models—0
Large Language Model Guided Knowledge Distillation for Time Series Anomaly Detection—0
Show:102550
← PrevPage 27 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