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 2451–2500 of 4240 papers

TitleStatusHype
Federated Learning on Non-iid Data via Local and Global Distillation—0
Cross Architecture Distillation for Face Recognition—0
Enhancing Mapless Trajectory Prediction through Knowledge Distillation—0
Feature Adversarial Distillation for Point Cloud Classification—0
On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes—0
Temporal Action Proposal Generation With Action Frequency Adaptive NetworkCode0
Incorporating Graph Information in Transformer-based AMR ParsingCode0
Knowledge Distillation via Token-level Relationship Graph—0
Recent Advances in Direct Speech-to-text Translation—0
Categories of Response-Based, Feature-Based, and Relation-Based Knowledge Distillation—0
FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation—0
Semi-Supervised Learning for Multi-Label Cardiovascular Diseases Prediction:A Multi-Dataset Study—0
MixedTeacher : Knowledge Distillation for fast inference textural anomaly detectionCode0
Knowledge Distillation for Efficient Audio-Visual Video Captioning—0
Squeezing nnU-Nets with Knowledge Distillation for On-Board Cloud Detection—0
Bridging the Gap between Decision and Logits in Decision-based Knowledge Distillation for Pre-trained Language ModelsCode0
Self-Knowledge Distillation for Surgical Phase Recognition—0
Heterogeneous Continual Learning—0
Enhanced Multimodal Representation Learning with Cross-modal KD—0
EaSyGuide : ESG Issue Identification Framework leveraging Abilities of Generative Large Language ModelsCode0
Improving Frame-level Classifier for Word Timings with Non-peaky CTC in End-to-End Automatic Speech Recognition—0
BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping—0
The economic trade-offs of large language models: A case study—0
Population-Based Evolutionary Gaming for Unsupervised Person Re-identification—0
Faithful Knowledge Distillation—0
Model-Based Reinforcement Learning with Multi-Task Offline PretrainingCode0
Zero shot framework for satellite image restoration—0
Joint Pre-training and Local Re-training: Transferable Representation Learning on Multi-source Knowledge GraphsCode0
Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient Inference—0
Deep Classifier Mimicry without Data AccessCode0
Evolving Knowledge Mining for Class Incremental SegmentationCode0
Privacy Distillation: Reducing Re-identification Risk of Multimodal Diffusion Models—0
Group channel pruning and spatial attention distilling for object detection—0
Speech Translation with Foundation Models and Optimal Transport: UPC at IWSLT23—0
Teacher Agent: A Knowledge Distillation-Free Framework for Rehearsal-based Video Incremental LearningCode0
Improved Cross-Lingual Transfer Learning For Automatic Speech Translation—0
Graph Entropy Minimization for Semi-supervised Node ClassificationCode0
Accurate and Structured Pruning for Efficient Automatic Speech Recognition—0
Research on Multilingual News Clustering Based on Cross-Language Word Embeddings—0
A Recipe for Efficient SBIR Models: Combining Relative Triplet Loss with Batch Normalization and Knowledge Distillation—0
KEYword based Sampling (KEYS) for Large Language Models—0
Bridging the Sim-to-Real Gap from the Information Bottleneck PerspectiveCode0
GripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Ranking—0
ConaCLIP: Exploring Distillation of Fully-Connected Knowledge Interaction Graph for Lightweight Text-Image Retrieval—0
Vision Transformers for Small Histological Datasets Learned through Knowledge DistillationCode0
Knowledge Distillation Performs Partial Variance ReductionCode0
ABC-KD: Attention-Based-Compression Knowledge Distillation for Deep Learning-Based Noise Suppression—0
A Study on Knowledge Distillation from Weak Teacher for Scaling Up Pre-trained Language Models—0
Knowledge Distillation for Neural Transducer-based Target-Speaker ASR: Exploiting Parallel Mixture/Single-Talker Speech Data—0
Camera-Incremental Object Re-Identification with Identity Knowledge EvolutionCode0
Show:102550
← PrevPage 50 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