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 2251–2300 of 4240 papers

TitleStatusHype
SMOC-Net: Leveraging Camera Pose for Self-Supervised Monocular Object Pose Estimation—0
Distilling Cross-Temporal Contexts for Continuous Sign Language Recognition—0
X3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detection—0
Bilateral Memory Consolidation for Continual Learning—0
Incrementer: Transformer for Class-Incremental Semantic Segmentation With Knowledge Distillation Focusing on Old Class—0
Active Exploration of Multimodal Complementarity for Few-Shot Action Recognition—0
Revisiting Prototypical Network for Cross Domain Few-Shot LearningCode1
Few-Shot Class-Incremental Learning via Class-Aware Bilateral DistillationCode1
CaPriDe Learning: Confidential and Private Decentralized Learning Based on Encryption-Friendly Distillation LossCode0
You Do Not Need Additional Priors or Regularizers in Retinex-Based Low-Light Image Enhancement—0
Open-Set Fine-Grained Retrieval via Prompting Vision-Language Evaluator—0
MEDIC: Remove Model Backdoors via Importance Driven Cloning—0
Rethinking Feature-Based Knowledge Distillation for Face Recognition—0
DaFKD: Domain-Aware Federated Knowledge Distillation—0
CLIPPING: Distilling CLIP-Based Models With a Student Base for Video-Language Retrieval—0
Distilling Focal Knowledge From Imperfect Expert for 3D Object DetectionCode0
Endpoints Weight Fusion for Class Incremental Semantic Segmentation—0
Boosting Accuracy and Robustness of Student Models via Adaptive Adversarial Distillation—0
FedICT: Federated Multi-task Distillation for Multi-access Edge ComputingCode0
Discriminator-Cooperated Feature Map Distillation for GAN CompressionCode1
Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental LearningCode1
A Unified Object Counting Network with Object Occupation PriorCode0
NeRN -- Learning Neural Representations for Neural NetworksCode1
Prototype-guided Cross-task Knowledge Distillation for Large-scale ModelsCode0
BD-KD: Balancing the Divergences for Online Knowledge Distillation—0
CAMeMBERT: Cascading Assistant-Mediated Multilingual BERT—0
UNIKD: UNcertainty-filtered Incremental Knowledge Distillation for Neural Implicit RepresentationCode0
RangeAugment: Efficient Online Augmentation with Range Learning—0
Fine-Grained Distillation for Long Document Retrieval—0
Diffusion Glancing Transformer for Parallel Sequence to Sequence Learning—0
Adam: Dense Retrieval Distillation with Adaptive Dark Examples—0
Multi-View Knowledge Distillation from Crowd Annotations for Out-of-Domain Generalization—0
I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation—0
KNIFE: Distilling Reasoning Knowledge From Free-Text Rationales—0
Learning Object-level Point Augmentor for Semi-supervised 3D Object DetectionCode1
Continual Knowledge Distillation for Neural Machine TranslationCode0
3D Point Cloud Pre-training with Knowledge Distillation from 2D Images—0
Teaching Small Language Models to Reason—0
Swing Distillation: A Privacy-Preserving Knowledge Distillation Framework—0
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?Code1
Gradient-based Intra-attention Pruning on Pre-trained Language ModelsCode1
Hybrid Paradigm-based Brain-Computer Interface for Robotic Arm Control—0
Domain Adaptation for Dense Retrieval through Self-Supervision by Pseudo-Relevance Labeling—0
Siamese Sleep Transformer For Robust Sleep Stage Scoring With Self-knowledge Distillation and Selective Batch Sampling—0
Multimodal Matching-aware Co-attention Networks with Mutual Knowledge Distillation for Fake News Detection—0
Continuation KD: Improved Knowledge Distillation through the Lens of Continuation Optimization—0
Towards Practical Plug-and-Play Diffusion ModelsCode1
Improving Generalization of Pre-trained Language Models via Stochastic Weight Averaging—0
Multi-adversarial Faster-RCNN with Paradigm Teacher for Unrestricted Object Detection—0
Teaching What You Should Teach: A Data-Based Distillation Method—0
Show:102550
← PrevPage 46 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