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 2701–2750 of 4240 papers

TitleStatusHype
MiniDisc: Minimal Distillation Schedule for Language Model CompressionCode0
Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box PredictorsCode1
One Reference Is Not Enough: Diverse Distillation with Reference Selection for Non-Autoregressive TranslationCode0
Parameter-Efficient and Student-Friendly Knowledge Distillation—0
Geometer: Graph Few-Shot Class-Incremental Learning via Prototype RepresentationCode1
Continual evaluation for lifelong learning: Identifying the stability gapCode1
Region-aware Knowledge Distillation for Efficient Image-to-Image Translation—0
Do we need Label Regularization to Fine-tune Pre-trained Language Models?—0
DFM: Dialogue Foundation Model for Universal Large-Scale Dialogue-Oriented Task Learning—0
Compressing Deep Graph Neural Networks via Adversarial Knowledge DistillationCode1
Optimizing Performance of Federated Person Re-identification: Benchmarking and AnalysisCode1
CDFKD-MFS: Collaborative Data-free Knowledge Distillation via Multi-level Feature SharingCode0
IDEAL: Query-Efficient Data-Free Learning from Black-box ModelsCode1
Boosting Multi-Label Image Classification with Complementary Parallel Self-DistillationCode1
PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D DetectionCode1
LILA-BOTI : Leveraging Isolated Letter Accumulations By Ordering Teacher Insights for Bangla Handwriting RecognitionCode0
Knowledge Distillation via the Target-aware TransformerCode1
Aligning Logits Generatively for Principled Black-Box Knowledge DistillationCode0
Knowledge Distillation from A Stronger TeacherCode1
Exploring Extreme Parameter Compression for Pre-trained Language ModelsCode1
InDistill: Information flow-preserving knowledge distillation for model compressionCode0
Simple Regularisation for Uncertainty-Aware Knowledge Distillation—0
ERNIE-Search: Bridging Cross-Encoder with Dual-Encoder via Self On-the-fly Distillation for Dense Passage Retrieval—0
Prompting to Distill: Boosting Data-Free Knowledge Distillation via Reinforced Prompt—0
Chemical transformer compression for accelerating both training and inference of molecular modelingCode0
Directed Acyclic Transformer for Non-Autoregressive Machine TranslationCode1
Not to Overfit or Underfit the Source Domains? An Empirical Study of Domain Generalization in Question Answering—0
Knowledge Distillation Meets Open-Set Semi-Supervised LearningCode1
"Teaching Independent Parts Separately" (TIPSy-GAN) : Improving Accuracy and Stability in Unsupervised Adversarial 2D to 3D Pose Estimation—0
D3T-GAN: Data-Dependent Domain Transfer GANs for Few-shot Image Generation—0
Knowledge Distillation for Multi-Target Domain Adaptation in Real-Time Person Re-IdentificationCode0
DistilProtBert: A distilled protein language model used to distinguish between real proteins and their randomly shuffled counterpartsCode1
Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learning—0
Data-Free Adversarial Knowledge Distillation for Graph Neural Networks—0
ConceptDistil: Model-Agnostic Distillation of Concept Explanations—0
Automatic Block-wise Pruning with Auxiliary Gating Structures for Deep Convolutional Neural Networks—0
Distilling Inter-Class Distance for Semantic Segmentation—0
Collective Relevance Labeling for Passage RetrievalCode0
Alignahead: Online Cross-Layer Knowledge Extraction on Graph Neural NetworksCode0
Holistic Approach to Measure Sample-level Adversarial Vulnerability and its Utility in Building Trustworthy Systems—0
A Deep Reinforcement Learning Framework for Rapid Diagnosis of Whole Slide Pathological Images—0
Spot-adaptive Knowledge DistillationCode1
FedSPLIT: One-Shot Federated Recommendation System Based on Non-negative Joint Matrix Factorization and Knowledge Distillation—0
Attention-based Knowledge Distillation in Multi-attention Tasks: The Impact of a DCT-driven Loss—0
Knowledge Distillation of Russian Language Models with Reduction of VocabularyCode0
Generalized Knowledge Distillation via Relationship MatchingCode0
Masked Generative DistillationCode2
FedDKD: Federated Learning with Decentralized Knowledge Distillation—0
Redistributing Low-Frequency Words: Making the Most of Monolingual Data in Non-Autoregressive TranslationCode0
Knowledge Distillation Meets Few-Shot Learning: An Approach for Few-Shot Intent Classification Within and Across Domains—0
Show:102550
← PrevPage 55 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