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 2551–2600 of 4240 papers

TitleStatusHype
Bidirectional Distillation: A Mixed-Play Framework for Multi-Agent Generalizable Behaviors—0
Ground Reaction Force Estimation via Time-aware Knowledge Distillation—0
3D-Augmented Contrastive Knowledge Distillation for Image-based Object Pose Estimation—0
3D Denoisers are Good 2D Teachers: Molecular Pretraining via Denoising and Cross-Modal Distillation—0
3D Face Alignment Through Fusion of Head Pose Information and Features—0
3D Point Cloud Pre-training with Knowledge Distillation from 2D Images—0
A baseline revisited: Pushing the limits of multi-segment models for context-aware translation—0
A Bayesian Optimization Framework for Neural Network Compression—0
ABC-KD: Attention-Based-Compression Knowledge Distillation for Deep Learning-Based Noise Suppression—0
ABKD: Graph Neural Network Compression with Attention-Based Knowledge Distillation—0
ACAM-KD: Adaptive and Cooperative Attention Masking for Knowledge Distillation—0
Accelerating Diffusion Models with One-to-Many Knowledge Distillation—0
Accelerating Large Scale Knowledge Distillation via Dynamic Importance Sampling—0
Accelerating Molecular Graph Neural Networks via Knowledge Distillation—0
Accelerating Transformer Decoding via a Hybrid of Self-attention and Recurrent Neural Network—0
Accurate and Structured Pruning for Efficient Automatic Speech Recognition—0
Accurate Knowledge Distillation with n-best Reranking—0
A Classifier-Free Incremental Learning Framework for Scalable Medical Image Segmentation—0
A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and Distillation—0
A Closer Look at Knowledge Distillation with Features, Logits, and Gradients—0
A Closer Look at Rehearsal-Free Continual Learning—0
A Closer Look at Wav2Vec2 Embeddings for On-Device Single-Channel Speech Enhancement—0
A Cohesive Distillation Architecture for Neural Language Models—0
A Comparative Analysis of Task-Agnostic Distillation Methods for Compressing Transformer Language Models—0
Supervised domain adaptation for building extraction from off-nadir aerial images—0
A Comprehensive Overhaul of Distilling Unconditional GANs—0
A Comprehensive Review of Knowledge Distillation in Computer Vision—0
A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks—0
A Comprehensive Survey of Compression Algorithms for Language Models—0
A Comprehensive Survey on Knowledge Distillation of Diffusion Models—0
A Continual and Incremental Learning Approach for TinyML On-device Training Using Dataset Distillation and Model Size Adaption—0
A Contrastive Teacher-Student Framework for Novelty Detection under Style Shifts—0
Acquiring Knowledge from Pre-trained Model to Neural Machine Translation—0
A Cross-Domain Approach for Continuous Impression Recognition from Dyadic Audio-Visual-Physio Signals—0
Action Spotting and Precise Event Detection in Sports: Datasets, Methods, and Challenges—0
Activation Map Adaptation for Effective Knowledge Distillation—0
Active Class Incremental Learning for Imbalanced Datasets—0
Active Data Curation Effectively Distills Large-Scale Multimodal Models—0
Active Exploration of Multimodal Complementarity for Few-Shot Action Recognition—0
Active Large Language Model-based Knowledge Distillation for Session-based Recommendation—0
Active Learning for Lane Detection: A Knowledge Distillation Approach—0
ActivityCLIP: Enhancing Group Activity Recognition by Mining Complementary Information from Text to Supplement Image Modality—0
Ada-DQA: Adaptive Diverse Quality-aware Feature Acquisition for Video Quality Assessment—0
AdaKD: Dynamic Knowledge Distillation of ASR models using Adaptive Loss Weighting—0
Adam: Dense Retrieval Distillation with Adaptive Dark Examples—0
Adapt-and-Distill: Developing Small, Fast and Effective Pretrained Language Models for Domains—0
Adapter-based Selective Knowledge Distillation for Federated Multi-domain Meeting Summarization—0
AdapterDistillation: Non-Destructive Task Composition with Knowledge Distillation—0
Adapting Models to Signal Degradation using Distillation—0
Adapting OC20-trained EquiformerV2 Models for High-Entropy Materials—0
Show:102550
← PrevPage 52 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