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 1251–1300 of 4240 papers

TitleStatusHype
Contrastive Representation Distillation via Multi-Scale Feature Decoupling—0
Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detector—0
ATLAS: Autoformalizing Theorems through Lifting, Augmentation, and Synthesis of Data—0
Revisiting Intermediate-Layer Matching in Knowledge Distillation: Layer-Selection Strategy Doesn't Matter (Much)—0
BOLT: Bootstrap Long Chain-of-Thought in Language Models without Distillation—0
Multilingual Non-Autoregressive Machine Translation without Knowledge DistillationCode0
A Unified Knowledge-Distillation and Semi-Supervised Learning Framework to Improve Industrial Ads Delivery Systems—0
Training an LLM-as-a-Judge Model: Pipeline, Insights, and Practical Lessons—0
MIND: Modality-Informed Knowledge Distillation Framework for Multimodal Clinical Prediction Tasks—0
A Framework for Double-Blind Federated Adaptation of Foundation Models—0
A method for estimating forest carbon storage distribution density via artificial intelligence generated content model—0
VLM-Assisted Continual learning for Visual Question Answering in Self-Driving—0
FedHPD: Heterogeneous Federated Reinforcement Learning via Policy DistillationCode0
Role of Mixup in Topological Persistence Based Knowledge Distillation for Wearable Sensor Data—0
Robust Knowledge Distillation in Federated Learning: Counteracting Backdoor AttacksCode0
Rethinking the Upsampling Layer in Hyperspectral Image Super Resolution—0
Mini-ResEmoteNet: Leveraging Knowledge Distillation for Human-Centered Design—0
RL-based Query Rewriting with Distilled LLM for online E-Commerce Systems—0
Distilling Knowledge for Designing Computational Imaging SystemsCode0
Efficient Knowledge Distillation of SAM for Medical Image Segmentation—0
Heterogeneity-aware Personalized Federated Learning via Adaptive Dual-Agent Reinforcement Learning—0
FedEFM: Federated Endovascular Foundation Model with Unseen Data—0
TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models—0
Target-driven Self-Distillation for Partial Observed Trajectories Forecasting—0
A Contrastive Teacher-Student Framework for Novelty Detection under Style Shifts—0
Efficient Logit-based Knowledge Distillation of Deep Spiking Neural Networks for Full-Range Timestep DeploymentCode0
PISCO: Pretty Simple Compression for Retrieval-Augmented Generation—0
MimicGait: A Model Agnostic approach for Occluded Gait Recognition using Correlational Knowledge DistillationCode0
Scaling Large Vision-Language Models for Enhanced Multimodal Comprehension In Biomedical Image Analysis—0
Graph-Based Cross-Domain Knowledge Distillation for Cross-Dataset Text-to-Image Person Retrieval—0
Pre-trained Model Guided Mixture Knowledge Distillation for Adversarial Federated Learning—0
On Accelerating Edge AI: Optimizing Resource-Constrained Environments—0
Multimodal Prescriptive Deep Learning—0
Remining Hard Negatives for Generative Pseudo Labeled Domain Adaptation—0
Multi-aspect Knowledge Distillation with Large Language ModelCode0
Unlearning Clients, Features and Samples in Vertical Federated Learning—0
Toward Model-centric Heterogeneous Federated Graph Learning: A Knowledge-driven Approach—0
EchoLM: Accelerating LLM Serving with Real-time Knowledge Distillation—0
LiT: Delving into a Simplified Linear Diffusion Transformer for Image Generation—0
Extracting General-use Transformers for Low-resource Languages via Knowledge Distillation—0
Efficient Lung Ultrasound Severity Scoring Using Dedicated Feature ExtractorCode0
Learning to reconstruct signals with inexact sensing operator via knowledge distillation—0
DNA 1.0 Technical Report—0
Enhancing Generalization in Chain of Thought Reasoning for Smaller Models—0
Soft Knowledge Distillation with Multi-Dimensional Cross-Net Attention for Image Restoration Models Compression—0
Class Incremental Fault Diagnosis under Limited Fault Data via Supervised Contrastive Knowledge DistillationCode0
Knowledge Distillation for Image Restoration : Simultaneous Learning from Degraded and Clean Images—0
Feature-based One-For-All: A Universal Framework for Heterogeneous Knowledge Distillation—0
VECT-GAN: A variationally encoded generative model for overcoming data scarcity in pharmaceutical scienceCode0
Induced Model Matching: Restricted Models Help Train Full-Featured ModelsCode0
Show:102550
← PrevPage 26 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