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 1501–1550 of 4240 papers

TitleStatusHype
Wired Perspectives: Multi-View Wire Art Embraces Generative AI—0
Unlearning via Sparse Representations—0
Double Reverse Regularization Network Based on Self-Knowledge Distillation for SAR Object Classification—0
Cosine Similarity Knowledge Distillation for Individual Class Information Transfer—0
Maximizing Discrimination Capability of Knowledge Distillation with Energy Function—0
Efficient Open-world Reinforcement Learning via Knowledge Distillation and Autonomous Rule Discovery—0
Pseudo-label Correction for Instance-dependent Noise Using Teacher-student Framework—0
Knowledge Distillation Based Semantic Communications For Multiple Users—0
Efficient and Robust Jet Tagging at the LHC with Knowledge DistillationCode0
Some Like It Small: Czech Semantic Embedding Models for Industry ApplicationsCode1
Bridging Classical and Quantum Machine Learning: Knowledge Transfer From Classical to Quantum Neural Networks Using Knowledge Distillation—0
Robustness-Reinforced Knowledge Distillation with Correlation Distance and Network Pruning—0
Education distillation:getting student models to learn in shcools—0
Efficient Transformer Knowledge Distillation: A Performance Review—0
EA-KD: Entropy-based Adaptive Knowledge Distillation—0
Point, Segment and Count: A Generalized Framework for Object CountingCode1
HoVer-UNet: Accelerating HoVerNet with UNet-based multi-class nuclei segmentation via knowledge distillationCode1
FreeKD: Knowledge Distillation via Semantic Frequency PromptCode1
Unveiling the Unseen Potential of Graph Learning through MLPs: Effective Graph Learners Using Propagation-Embracing MLPs—0
Expanding Scene Graph Boundaries: Fully Open-vocabulary Scene Graph Generation via Visual-Concept Alignment and RetentionCode1
LightBTSeg: A lightweight breast tumor segmentation model using ultrasound images via dual-path joint knowledge distillation—0
Rethinking Attention: Exploring Shallow Feed-Forward Neural Networks as an Alternative to Attention Layers in Transformers—0
Semi-supervised ViT knowledge distillation network with style transfer normalization for colorectal liver metastases survival prediction—0
A Knowledge Distillation Approach for Sepsis Outcome Prediction from Multivariate Clinical Time Series—0
Multistage Collaborative Knowledge Distillation from a Large Language Model for Semi-Supervised Sequence GenerationCode0
Unlock the Power: Competitive Distillation for Multi-Modal Large Language Models—0
Distilling the Unknown to Unveil CertaintyCode0
Batch Selection and Communication for Active Learning with Edge Labeling—0
Teach me with a Whisper: Enhancing Large Language Models for Analyzing Spoken Transcripts using Speech Embeddings—0
On Elastic Language Models—0
Quantized Distillation: Optimizing Driver Activity Recognition Models for Resource-Constrained EnvironmentsCode1
DONUT-hole: DONUT Sparsification by Harnessing Knowledge and Optimizing Learning Efficiency—0
Text Representation Distillation via Information Bottleneck PrincipleCode0
Object-centric Cross-modal Feature Distillation for Event-based Object Detection—0
Bridging Dimensions: Confident Reachability for High-Dimensional ControllersCode0
Preference-Consistent Knowledge Distillation for Recommender SystemCode0
What is Lost in Knowledge Distillation?—0
Supervised domain adaptation for building extraction from off-nadir aerial images—0
Data exploitation: multi-task learning of object detection and semantic segmentation on partially annotated dataCode0
Reducing Spatial Fitting Error in Distillation of Denoising Diffusion ModelsCode0
Asymmetric Masked Distillation for Pre-Training Small Foundation ModelsCode0
Co-training and Co-distillation for Quality Improvement and Compression of Language Models—0
Cross-Level Distillation and Feature Denoising for Cross-Domain Few-Shot ClassificationCode1
After-Stroke Arm Paresis Detection using Kinematic Data—0
Comparative Knowledge DistillationCode0
Data-Free Distillation of Language Model by Text-to-Text Transfer—0
Distilling Out-of-Distribution Robustness from Vision-Language Foundation ModelsCode1
An Efficient Detection and Control System for Underwater Docking using Machine Learning and Realistic Simulation: A Comprehensive Approach—0
Multilingual DistilWhisper: Efficient Distillation of Multi-task Speech Models via Language-Specific ExpertsCode1
Implicit Chain of Thought Reasoning via Knowledge DistillationCode1
Show:102550
← PrevPage 31 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