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 1701–1750 of 4240 papers

TitleStatusHype
Edge Bias in Federated Learning and its Solution by Buffered Knowledge Distillation—0
Galileo at SemEval-2020 Task 12: Multi-lingual Learning for Offensive Language Identification using Pre-trained Language Models—0
ActivityCLIP: Enhancing Group Activity Recognition by Mining Complementary Information from Text to Supplement Image Modality—0
GAN-Knowledge Distillation for one-stage Object Detection—0
Gap Preserving Distillation by Building Bidirectional Mappings with A Dynamic Teacher—0
GazeGen: Gaze-Driven User Interaction for Visual Content Generation—0
End-to-End Automatic Speech Recognition with Deep Mutual Learning—0
Endpoints Weight Fusion for Class Incremental Semantic Segmentation—0
EncodeNet: A Framework for Boosting DNN Accuracy with Entropy-driven Generalized Converting Autoencoder—0
Enabling Weak Client Participation via On-device Knowledge Distillation in Heterogenous Federated Learning—0
Compositional Data Augmentation for Abstractive Conversation Summarization—0
Asynchronous Convergence in Multi-Task Learning via Knowledge Distillation from Converged Tasks—0
Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation—0
Generalized Continual Zero-Shot Learning—0
Data Efficient Acoustic Scene Classification using Teacher-Informed Confusing Class Instruction—0
Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation—0
Generalized Uncertainty of Deep Neural Networks: Taxonomy and Applications—0
Data-efficient Event Camera Pre-training via Disentangled Masked Modeling—0
Asymmetric Temperature Scaling Makes Larger Networks Teach Well Again—0
General Purpose Text Embeddings from Pre-trained Language Models for Scalable Inference—0
Generate, Annotate, and Learn: Generative Models Advance Self-Training and Knowledge Distillation—0
Generating Long Financial Report using Conditional Variational Autoencoders with Knowledge Distillation—0
Complex Emotion Recognition System using basic emotions via Facial Expression, EEG, and ECG Signals: a review—0
Generation and Consolidation of Recollections for Efficient Deep Lifelong Learning—0
Generation-Distillation for Efficient Natural Language Understanding in Low-Data Settings—0
Generative Adversarial Simulator—0
Empowering Knowledge Distillation via Open Set Recognition for Robust 3D Point Cloud Classification—0
AfroXLMR-Comet: Multilingual Knowledge Distillation with Attention Matching for Low-Resource languages—0
I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation—0
I^2KD-SLU: An Intra-Inter Knowledge Distillation Framework for Zero-Shot Cross-Lingual Spoken Language Understanding—0
Empowering Dual-Encoder with Query Generator for Cross-Lingual Dense Retrieval—0
Empirical Evaluation of Knowledge Distillation from Transformers to Subquadratic Language Models—0
Complete-to-Partial 4D Distillation for Self-Supervised Point Cloud Sequence Representation Learning—0
Knowledge distillation for optimization of quantized deep neural networks—0
Emo Pillars: Knowledge Distillation to Support Fine-Grained Context-Aware and Context-Less Emotion Classification—0
A Framework for Double-Blind Federated Adaptation of Foundation Models—0
Embracing the Dark Knowledge: Domain Generalization Using Regularized Knowledge Distillation—0
EmbedDistill: A Geometric Knowledge Distillation for Information Retrieval—0
Completely Heterogeneous Federated Learning—0
GhostNetV3: Exploring the Training Strategies for Compact Models—0
Embedding Compression for Teacher-to-Student Knowledge Transfer—0
On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes—0
Asymmetric Image Retrieval with Cross Model Compatible Ensembles—0
ABKD: Graph Neural Network Compression with Attention-Based Knowledge Distillation—0
Embedded Knowledge Distillation in Depth-Level Dynamic Neural Network—0
ELiTe: Efficient Image-to-LiDAR Knowledge Transfer for Semantic Segmentation—0
Comparison of Soft and Hard Target RNN-T Distillation for Large-scale ASR—0
Global Intervention and Distillation for Federated Out-of-Distribution Generalization—0
ADPS: Asymmetric Distillation Post-Segmentation for Image Anomaly Detection—0
VizECGNet: Visual ECG Image Network for Cardiovascular Diseases Classification with Multi-Modal Training and Knowledge Distillation—0
Show:102550
← PrevPage 35 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