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 39013950 of 4240 papers

TitleStatusHype
Towards Non-task-specific Distillation of BERT via Sentence Representation Approximation0
Enhancing Review Comprehension with Domain-Specific Commonsense0
Temporally Distributed Networks for Fast Video Semantic SegmentationCode1
More Grounded Image Captioning by Distilling Image-Text Matching ModelCode1
Knowledge as Priors: Cross-Modal Knowledge Generalization for Datasets without Superior Knowledge0
Creating Something from Nothing: Unsupervised Knowledge Distillation for Cross-Modal HashingCode1
Neural Networks Are More Productive Teachers Than Human Raters: Active Mixup for Data-Efficient Knowledge Distillation from a Blackbox ModelCode1
Distilled Semantics for Comprehensive Scene Understanding from VideosCode1
Spatio-Temporal Graph for Video Captioning with Knowledge Distillation0
SS-IL: Separated Softmax for Incremental Learning0
Regularizing Class-wise Predictions via Self-knowledge DistillationCode1
Squeezed Deep 6DoF Object Detection Using Knowledge DistillationCode0
Analysis of Knowledge Transfer in Kernel Regime0
Circumventing Outliers of AutoAugment with Knowledge DistillationCode1
A Survey of Methods for Low-Power Deep Learning and Computer Vision0
Synergic Adversarial Label Learning for Grading Retinal Diseases via Knowledge Distillation and Multi-task Learning0
Distilling Knowledge from Graph Convolutional NetworksCode1
Collaborative Distillation for Ultra-Resolution Universal Style TransferCode1
Incremental Object Detection via Meta-LearningCode1
Teacher-Student chain for efficient semi-supervised histology image classification0
Deformation Flow Based Two-Stream Network for Lip ReadingCode1
SuperMix: Supervising the Mixing Data AugmentationCode1
Knowledge distillation via adaptive instance normalization0
Faster ILOD: Incremental Learning for Object Detectors based on Faster RCNNCode1
Pacemaker: Intermediate Teacher Knowledge Distillation For On-The-Fly Convolutional Neural Network0
PoseNet3D: Learning Temporally Consistent 3D Human Pose via Knowledge DistillationCode1
Distilling portable Generative Adversarial Networks for Image Translation0
Explaining Knowledge Distillation by Quantifying the Knowledge0
Distill, Adapt, Distill: Training Small, In-Domain Models for Neural Machine Translation0
An Efficient Method of Training Small Models for Regression Problems with Knowledge Distillation0
TextBrewer: An Open-Source Knowledge Distillation Toolkit for Natural Language ProcessingCode2
Efficient Semantic Video Segmentation with Per-frame InferenceCode1
Semi-Supervised Speech Recognition via Local Prior MatchingCode3
Residual Knowledge Distillation0
Balancing Cost and Benefit with Tied-Multi Transformers0
The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding0
Knapsack Pruning with Inner DistillationCode1
Self-Distillation Amplifies Regularization in Hilbert Space0
Salvaging Federated Learning by Local AdaptationCode1
Content Based Singing Voice Extraction From a Musical MixtureCode0
Meta-Learning across Meta-Tasks for Few-Shot Learning0
Regularized Evolutionary Population-Based Training0
Knowledge Distillation for Brain Tumor SegmentationCode1
Understanding and Improving Knowledge Distillation0
Unlabeled Data Deployment for Classification of Diabetic Retinopathy Images Using Knowledge Transfer0
SUOD: Toward Scalable Unsupervised Outlier DetectionCode1
BERT-of-Theseus: Compressing BERT by Progressive Module ReplacingCode1
Feature-map-level Online Adversarial Knowledge Distillation0
Periodic Intra-Ensemble Knowledge Distillation for Reinforcement LearningCode0
Search for Better Students to Learn Distilled Knowledge0
Show:102550
← PrevPage 79 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