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 2601–2650 of 4240 papers

TitleStatusHype
Aware of the History: Trajectory Forecasting with the Local Behavior Data—0
Model Compression for Resource-Constrained Mobile Robots—0
Knowledge distillation with a class-aware loss for endoscopic disease detection—0
Context Unaware Knowledge Distillation for Image RetrievalCode0
FedX: Unsupervised Federated Learning with Cross Knowledge DistillationCode1
Informative knowledge distillation for image anomaly segmentationCode1
Learning Knowledge Representation with Meta Knowledge Distillation for Single Image Super-Resolution—0
Class-incremental Novel Class DiscoveryCode1
Rethinking Data Augmentation for Robust Visual Question AnsweringCode1
TSPipe: Learn from Teacher Faster with PipelinesCode0
Subclass Knowledge Distillation with Known Subclass Labels—0
SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detection—0
Multi-Level Branched Regularization for Federated LearningCode1
Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting—0
Rethinking Attention Mechanism in Time Series Classification—0
Large-scale Knowledge Distillation with Elastic Heterogeneous Computing ResourcesCode1
Deep versus Wide: An Analysis of Student Architectures for Task-Agnostic Knowledge Distillation of Self-Supervised Speech Models—0
Rich Feature Distillation with Feature Affinity Module for Efficient Image Dehazing—0
DSPNet: Towards Slimmable Pretrained Networks based on Discriminative Self-supervised Learning—0
ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-SpeechCode3
Re2G: Retrieve, Rerank, GenerateCode1
SlimSeg: Slimmable Semantic Segmentation with Boundary Supervision—0
Distilled Non-Semantic Speech Embeddings with Binary Neural Networks for Low-Resource DevicesCode0
Contrastive Deep SupervisionCode1
Normalized Feature Distillation for Semantic Segmentation—0
Knowledge Condensation DistillationCode1
HEAD: HEtero-Assists Distillation for Heterogeneous Object DetectorsCode1
Cross-Architecture Knowledge Distillation—0
Fast-Vid2Vid: Spatial-Temporal Compression for Video-to-Video SynthesisCode1
2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point CloudsCode2
1st Place Solution to the EPIC-Kitchens Action Anticipation Challenge 2022—0
FairDistillation: Mitigating Stereotyping in Language ModelsCode1
Improving Streaming End-to-End ASR on Transformer-based Causal Models with Encoder States Revision Strategies—0
Low-resource Low-footprint Wake-word Detection using Knowledge Distillation—0
PKD: General Distillation Framework for Object Detectors via Pearson Correlation Coefficient—0
GLANCE: Global to Local Architecture-Neutral Concept-based ExplanationsCode0
Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge TransferCode1
ACT-Net: Asymmetric Co-Teacher Network for Semi-supervised Memory-efficient Medical Image SegmentationCode0
A Generative Framework for Personalized Learning and Estimation: Theory, Algorithms, and Privacy—0
VEM^2L: A Plug-and-play Framework for Fusing Text and Structure Knowledge on Sparse Knowledge Graph Completion—0
FasterAI: A Lightweight Library for Creating Sparse Neural Networks—0
PrUE: Distilling Knowledge from Sparse Teacher NetworksCode0
Speech Emotion: Investigating Model Representations, Multi-Task Learning and Knowledge Distillation—0
Lost in Distillation: A Case Study in Toxicity Modeling—0
Asynchronous Convergence in Multi-Task Learning via Knowledge Distillation from Converged Tasks—0
KroneckerBERT: Significant Compression of Pre-trained Language Models Through Kronecker Decomposition and Knowledge Distillation—0
Why Knowledge Distillation Amplifies Gender Bias and How to Mitigate from the Perspective of DistilBERT—0
End-to-End Simultaneous Speech Translation with Pretraining and Distillation: Huawei Noah’s System for AutoSimTranS 2022—0
FitHuBERT: Going Thinner and Deeper for Knowledge Distillation of Speech Self-Supervised LearningCode1
ListBERT: Learning to Rank E-commerce products with Listwise BERT—0
Show:102550
← PrevPage 53 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