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

Showing 501550 of 4240 papers

TitleStatusHype
Language Model Prior for Low-Resource Neural Machine TranslationCode1
Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation ModelsCode1
Distillation Matters: Empowering Sequential Recommenders to Match the Performance of Large Language ModelCode1
Directed Acyclic Graph Factorization Machines for CTR Prediction via Knowledge DistillationCode1
Advancing Pre-trained Teacher: Towards Robust Feature Discrepancy for Anomaly DetectionCode1
Learning Compatible EmbeddingsCode1
A Deep Knowledge Distillation framework for EEG assisted enhancement of single-lead ECG based sleep stagingCode1
Learning Distilled Collaboration Graph for Multi-Agent PerceptionCode1
Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed ClassificationCode1
Learning Generalizable Models for Vehicle Routing Problems via Knowledge DistillationCode1
Directed Acyclic Transformer for Non-Autoregressive Machine TranslationCode1
Extending global-local view alignment for self-supervised learning with remote sensing imageryCode1
Digging into contrastive learning for robust depth estimation with diffusion modelsCode1
DIOD: Self-Distillation Meets Object DiscoveryCode1
DisCo: Distilled Student Models Co-training for Semi-supervised Text MiningCode1
Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual LearningCode1
Dice Semimetric Losses: Optimizing the Dice Score with Soft LabelsCode1
Channel Distillation: Channel-Wise Attention for Knowledge DistillationCode1
A Contrastive Distillation Approach for Incremental Semantic Segmentation in Aerial ImagesCode1
CheXseg: Combining Expert Annotations with DNN-generated Saliency Maps for X-ray SegmentationCode1
DiGA: Distil to Generalize and then Adapt for Domain Adaptive Semantic SegmentationCode1
DistilCSE: Effective Knowledge Distillation For Contrastive Sentence EmbeddingsCode1
Distilling the Knowledge of BERT for Sequence-to-Sequence ASRCode1
Densely Guided Knowledge Distillation using Multiple Teacher AssistantsCode1
Dense Interspecies Face EmbeddingCode1
DE-RRD: A Knowledge Distillation Framework for Recommender SystemCode1
Deliberated Domain Bridging for Domain Adaptive Semantic SegmentationCode1
A Dual-Space Framework for General Knowledge Distillation of Large Language ModelsCode1
Deliberation on Priors: Trustworthy Reasoning of Large Language Models on Knowledge GraphsCode1
DFIL: Deepfake Incremental Learning by Exploiting Domain-invariant Forgery CluesCode1
Deep Structured Instance Graph for Distilling Object DetectorsCode1
Deep Semi-supervised Knowledge Distillation for Overlapping Cervical Cell Instance SegmentationCode1
Defocus Blur Detection via Depth DistillationCode1
CEKD: Cross-Modal Edge-Privileged Knowledge Distillation for Semantic Scene Understanding Using Only Thermal ImagesCode1
DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation TrainerCode1
Deformation Flow Based Two-Stream Network for Lip ReadingCode1
DGEKT: A Dual Graph Ensemble Learning Method for Knowledge TracingCode1
Decoupled Multimodal Distilling for Emotion RecognitionCode1
Anti-Distillation Backdoor Attacks: Backdoors Can Really Survive in Knowledge DistillationCode1
DeepAqua: Self-Supervised Semantic Segmentation of Wetland Surface Water Extent with SAR Images using Knowledge DistillationCode1
Decomposed Knowledge Distillation for Class-Incremental Semantic SegmentationCode1
Decoupled Kullback-Leibler Divergence LossCode1
Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine TranslationCode1
Data-Free Knowledge Distillation via Feature Exchange and Activation Region ConstraintCode1
Data-Free Class-Incremental Hand Gesture RecognitionCode1
AD-KD: Attribution-Driven Knowledge Distillation for Language Model CompressionCode1
Data-Free Knowledge Distillation for Heterogeneous Federated LearningCode1
Data-Free Network Quantization With Adversarial Knowledge DistillationCode1
DASS: Distilled Audio State Space Models Are Stronger and More Duration-Scalable LearnersCode1
DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech TranslationCode1
Show:102550
← PrevPage 11 of 85Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ScaleKD (T:BEiT-L S:ViT-B/14)Top-1 accuracy %86.43Unverified
2ScaleKD (T:Swin-L S:ViT-B/16)Top-1 accuracy %85.53Unverified
3ScaleKD (T:Swin-L S:ViT-S/16)Top-1 accuracy %83.93Unverified
4ScaleKD (T:Swin-L S:Swin-T)Top-1 accuracy %83.8Unverified
5KD++(T: regnety-16GF S:ViT-B)Top-1 accuracy %83.6Unverified
6VkD (T:RegNety 160 S:DeiT-S)Top-1 accuracy %82.9Unverified
7SpectralKD (T:Swin-S S:Swin-T)Top-1 accuracy %82.7Unverified
8ScaleKD (T:Swin-L S:ResNet-50)Top-1 accuracy %82.55Unverified
9DiffKD (T:Swin-L S: Swin-T)Top-1 accuracy %82.5Unverified
10DIST (T: Swin-L S: Swin-T)Top-1 accuracy %82.3Unverified
#ModelMetricClaimedVerifiedStatus
1SRD (T:resnet-32x4, S:shufflenet-v2)Top-1 Accuracy (%)79.86Unverified
2shufflenet-v2(T:resnet-32x4, S:shufflenet-v2)Top-1 Accuracy (%)78.76Unverified
3MV-MR (T: CLIP/ViT-B-16 S: resnet50)Top-1 Accuracy (%)78.6Unverified
4resnet8x4 (T: resnet32x4 S: resnet8x4)Top-1 Accuracy (%)78.28Unverified
5resnet8x4 (T: resnet32x4 S: resnet8x4 [modified])Top-1 Accuracy (%)78.08Unverified
6ReviewKD++(T:resnet-32x4, S:shufflenet-v2)Top-1 Accuracy (%)77.93Unverified
7ReviewKD++(T:resnet-32x4, S:shufflenet-v1)Top-1 Accuracy (%)77.68Unverified
8resnet8x4 (T: resnet32x4 S: resnet8x4)Top-1 Accuracy (%)77.5Unverified
9resnet8x4 (T: resnet32x4 S: resnet8x4)Top-1 Accuracy (%)76.68Unverified
10resnet8x4 (T: resnet32x4 S: resnet8x4)Top-1 Accuracy (%)76.31Unverified
#ModelMetricClaimedVerifiedStatus
1LSHFM (T: ResNet101 S: ResNet50)mAP93.17Unverified
2LSHFM (T: ResNet101 S: MobileNetV2)mAP90.14Unverified
#ModelMetricClaimedVerifiedStatus
1TIE-KD (T: Adabins S: MobileNetV2)RMSE2.43Unverified