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 1901–1950 of 4240 papers

TitleStatusHype
Cross-Lingual Knowledge Distillation for Answer Sentence Selection in Low-Resource Languages—0
OVO: Open-Vocabulary OccupancyCode1
Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments—0
Collective Knowledge Graph Completion with Mutual Knowledge Distillation—0
Knowledge Distillation for Neural Transducer-based Target-Speaker ASR: Exploiting Parallel Mixture/Single-Talker Speech Data—0
Triplet Knowledge Distillation—0
Camera-Incremental Object Re-Identification with Identity Knowledge EvolutionCode0
How to Distill your BERT: An Empirical Study on the Impact of Weight Initialisation and Distillation ObjectivesCode1
HARD: Hard Augmentations for Robust Distillation—0
Incorporating Ultrasound Tongue Images for Audio-Visual Speech Enhancement through Knowledge Distillation—0
CoLaDa: A Collaborative Label Denoising Framework for Cross-lingual Named Entity RecognitionCode2
Deakin RF-Sensing: Experiments on Correlated Knowledge Distillation for Monitoring Human Postures with Radios—0
Just CHOP: Embarrassingly Simple LLM Compression—0
AdvFunMatch: When Consistent Teaching Meets Adversarial Robustness—0
PruMUX: Augmenting Data Multiplexing with Model CompressionCode0
NORM: Knowledge Distillation via N-to-One Representation MatchingCode1
Sequence-Level Knowledge Distillation for Class-Incremental End-to-End Spoken Language Understanding—0
One-stop Training of Multiple Capacity Models—0
Masked Modeling Duo for Speech: Specializing General-Purpose Audio Representation to Speech using Denoising Distillation—0
Decoupled Kullback-Leibler Divergence LossCode1
Transferring Learning Trajectories of Neural Networks—0
EnSiam: Self-Supervised Learning With Ensemble Representations—0
Distilling Robustness into Natural Language Inference Models with Domain-Targeted Augmentation—0
Lion: Adversarial Distillation of Proprietary Large Language ModelsCode2
Is Synthetic Data From Diffusion Models Ready for Knowledge Distillation?Code1
D^2TV: Dual Knowledge Distillation and Target-oriented Vision Modeling for Many-to-Many Multimodal SummarizationCode0
Revisiting Data Augmentation in Model Compression: An Empirical and Comprehensive Study—0
Understanding the Effect of Data Augmentation on Knowledge Distillation—0
DualVC: Dual-mode Voice Conversion using Intra-model Knowledge Distillation and Hybrid Predictive Coding—0
One-Shot Federated Learning for LEO Constellations that Reduces Convergence Time from Days to 90 Minutes—0
DisCo: Distilled Student Models Co-training for Semi-supervised Text MiningCode1
Lifting the Curse of Capacity Gap in Distilling Language ModelsCode1
Accurate Knowledge Distillation with n-best Reranking—0
Sentence Embedder Guided Utterance Encoder (SEGUE) for Spoken Language UnderstandingCode0
Pseudo-Label Training and Model Inertia in Neural Machine Translation—0
Boost Vision Transformer with GPU-Friendly Sparsity and Quantization—0
BERM: Training the Balanced and Extractable Representation for Matching to Improve Generalization Ability of Dense Retrieval—0
Cross-modality Data Augmentation for End-to-End Sign Language TranslationCode1
DQ-Whisper: Joint Distillation and Quantization for Efficient Multilingual Speech Recognition—0
Student-friendly Knowledge Distillation—0
Catch-Up Distillation: You Only Need to Train Once for Accelerating SamplingCode0
AD-KD: Attribution-Driven Knowledge Distillation for Language Model CompressionCode1
When Gradient Descent Meets Derivative-Free Optimization: A Match Made in Black-Box Scenario—0
Tailoring Instructions to Student's Learning Levels Boosts Knowledge DistillationCode1
Weight-Inherited Distillation for Task-Agnostic BERT CompressionCode0
Lightweight Self-Knowledge Distillation with Multi-source Information FusionCode0
Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation ModelsCode1
Soft Prompt Decoding for Multilingual Dense Retrieval—0
Distilling Knowledge for Short-to-Long Term Trajectory Prediction—0
Improving Defensive Distillation using Teacher Assistant—0
Show:102550
← PrevPage 39 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