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 301–350 of 4240 papers

TitleStatusHype
Content-Aware GAN CompressionCode1
Consistent Representation Learning for Continual Relation ExtractionCode1
Content-Variant Reference Image Quality Assessment via Knowledge DistillationCode1
Contrastive Distillation on Intermediate Representations for Language Model CompressionCode1
Conformer and Blind Noisy Students for Improved Image Quality AssessmentCode1
Confidence-Aware Multi-Teacher Knowledge DistillationCode1
CoNMix for Source-free Single and Multi-target Domain AdaptationCode1
ConcealGS: Concealing Invisible Copyright Information in 3D Gaussian SplattingCode1
Computation-Efficient Knowledge Distillation via Uncertainty-Aware MixupCode1
ConNER: Consistency Training for Cross-lingual Named Entity RecognitionCode1
SKDF: A Simple Knowledge Distillation Framework for Distilling Open-Vocabulary Knowledge to Open-world Object DetectorCode1
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language GuidanceCode1
ConStyle v2: A Strong Prompter for All-in-One Image RestorationCode1
Designing Large Foundation Models for Efficient Training and Inference: A SurveyCode1
Context-Aware Image Inpainting with Learned Semantic PriorsCode1
Continual All-in-One Adverse Weather Removal with Knowledge Replay on a Unified Network StructureCode1
Continual evaluation for lifelong learning: Identifying the stability gapCode1
Continual Learning for Image Segmentation with Dynamic QueryCode1
A semi-supervised Teacher-Student framework for surgical tool detection and localizationCode1
Comprehensive Knowledge Distillation with Causal InterventionCode1
Complementary Relation Contrastive DistillationCode1
CrossKD: Cross-Head Knowledge Distillation for Object DetectionCode1
CrossMatch: Enhance Semi-Supervised Medical Image Segmentation with Perturbation Strategies and Knowledge DistillationCode1
Cross-Modal Fusion Distillation for Fine-Grained Sketch-Based Image RetrievalCode1
A Fast Knowledge Distillation Framework for Visual RecognitionCode1
Action knowledge for video captioning with graph neural networksCode1
Compressing Deep Graph Neural Networks via Adversarial Knowledge DistillationCode1
Prototype-based Incremental Few-Shot Semantic SegmentationCode1
Consensual Collaborative Training And Knowledge Distillation Based Facial Expression Recognition Under Noisy AnnotationsCode1
Curriculum Learning for Dense Retrieval DistillationCode1
AutoGAN-Distiller: Searching to Compress Generative Adversarial NetworksCode1
DARTS: Double Attention Reference-based Transformer for Super-resolutionCode1
DASS: Distilled Audio State Space Models Are Stronger and More Duration-Scalable LearnersCode1
Data Diversification: A Simple Strategy For Neural Machine TranslationCode1
Contrastive Model Inversion for Data-Free Knowledge DistillationCode1
A Symmetric Dual Encoding Dense Retrieval Framework for Knowledge-Intensive Visual Question AnsweringCode1
Data-Free Network Quantization With Adversarial Knowledge DistillationCode1
DA-Mamba: Domain Adaptive Hybrid Mamba-Transformer Based One-Stage Object DetectionCode1
Decoupled Kullback-Leibler Divergence LossCode1
Decoupled Multimodal Distilling for Emotion RecognitionCode1
Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine TranslationCode1
Deep Graph-level Anomaly Detection by Glocal Knowledge DistillationCode1
AgeFlow: Conditional Age Progression and Regression with Normalizing FlowsCode1
Defocus Blur Detection via Depth DistillationCode1
ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via α-β-DivergenceCode1
Deliberated Domain Bridging for Domain Adaptive Semantic SegmentationCode1
A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank CloneCode1
Avatar Knowledge Distillation: Self-ensemble Teacher Paradigm with UncertaintyCode1
DE-RRD: A Knowledge Distillation Framework for Recommender SystemCode1
Collaborative Distillation for Ultra-Resolution Universal Style TransferCode1
Show:102550
← PrevPage 7 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