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 17511800 of 4240 papers

TitleStatusHype
Leveraging Expert Models for Training Deep Neural Networks in Scarce Data Domains: Application to Offline Handwritten Signature Verification0
Spatio-Temporal Branching for Motion Prediction using Motion IncrementsCode0
Towards Better Query Classification with Multi-Expert Knowledge Condensation in JD Ads Search0
NormKD: Normalized Logits for Knowledge DistillationCode1
Ada-DQA: Adaptive Diverse Quality-aware Feature Acquisition for Video Quality Assessment0
Online Prototype Learning for Online Continual LearningCode1
Can Self-Supervised Representation Learning Methods Withstand Distribution Shifts and Corruptions?Code0
Federated Learning for Data and Model Heterogeneity in Medical Imaging0
BearingPGA-Net: A Lightweight and Deployable Bearing Fault Diagnosis Network via Decoupled Knowledge Distillation and FPGA AccelerationCode1
Sampling to Distill: Knowledge Transfer from Open-World Data0
Subspace Distillation for Continual LearningCode0
UPFL: Unsupervised Personalized Federated Learning towards New ClientsCode0
Effective Whole-body Pose Estimation with Two-stages DistillationCode4
f-Divergence Minimization for Sequence-Level Knowledge DistillationCode1
Incrementally-Computable Neural Networks: Efficient Inference for Dynamic Inputs0
Fitting Auditory Filterbanks with Multiresolution Neural NetworksCode1
Mitigating Cross-client GANs-based Attack in Federated Learning0
MetricGAN-OKD: Multi-Metric Optimization of MetricGAN via Online Knowledge Distillation for Speech EnhancementCode1
A Good Student is Cooperative and Reliable: CNN-Transformer Collaborative Learning for Semantic Segmentation0
CLIP-KD: An Empirical Study of CLIP Model DistillationCode1
HeteFedRec: Federated Recommender Systems with Model Heterogeneity0
Model Compression Methods for YOLOv5: A Review0
DPM-OT: A New Diffusion Probabilistic Model Based on Optimal TransportCode1
Distribution Shift Matters for Knowledge Distillation with Webly Collected Images0
Quantized Feature Distillation for Network Quantization0
Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns ClusteringCode0
Reverse Knowledge Distillation: Training a Large Model using a Small One for Retinal Image Matching on Limited DataCode1
LightPath: Lightweight and Scalable Path Representation LearningCode0
Teach model to answer questions after comprehending the document0
FedDefender: Client-Side Attack-Tolerant Federated LearningCode1
A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and FutureCode2
Knowledge Distillation for Object Detection: from generic to remote sensing datasets0
Class-relation Knowledge Distillation for Novel Class DiscoveryCode1
Domain Knowledge Distillation from Large Language Model: An Empirical Study in the Autonomous Driving Domain0
DARTS: Double Attention Reference-based Transformer for Super-resolutionCode1
Cumulative Spatial Knowledge Distillation for Vision TransformersCode1
DOT: A Distillation-Oriented TrainerCode2
Improving End-to-End Speech Translation by Imitation-Based Knowledge Distillation with Synthetic TranscriptsCode0
Cross-Lingual NER for Financial Transaction Data in Low-Resource Languages0
A Survey of Techniques for Optimizing Transformer Inference0
MinT: Boosting Generalization in Mathematical Reasoning via Multi-View Fine-Tuning0
Intuitive Access to Smartphone Settings Using Relevance Model Trained by Contrastive Learning0
SoccerKDNet: A Knowledge Distillation Framework for Action Recognition in Soccer Videos0
Learning to Retrieve In-Context Examples for Large Language ModelsCode1
DreamTeacher: Pretraining Image Backbones with Deep Generative Models0
Multimodal Distillation for Egocentric Action RecognitionCode1
A metric learning approach for endoscopic kidney stone identification0
Frameless Graph Knowledge DistillationCode0
Regression-Oriented Knowledge Distillation for Lightweight Ship Orientation Angle Prediction with Optical Remote Sensing ImagesCode0
The Staged Knowledge Distillation in Video Classification: Harmonizing Student Progress by a Complementary Weakly Supervised Framework0
Show:102550
← PrevPage 36 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