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
UB-FineNet: Urban Building Fine-grained Classification Network for Open-access Satellite Images—0
PowerSkel: A Device-Free Framework Using CSI Signal for Human Skeleton Estimation in Power StationCode0
A Closer Look at Wav2Vec2 Embeddings for On-Device Single-Channel Speech Enhancement—0
Align-to-Distill: Trainable Attention Alignment for Knowledge Distillation in Neural Machine TranslationCode0
Logit Standardization in Knowledge DistillationCode3
Hyperspectral Image Analysis in Single-Modal and Multimodal setting using Deep Learning Techniques—0
On the Road to Portability: Compressing End-to-End Motion Planner for Autonomous DrivingCode2
Teaching MLP More Graph Information: A Three-stage Multitask Knowledge Distillation Framework—0
Distilling Text Style Transfer With Self-Explanation From LLMs—0
Differentially Private Knowledge Distillation via Synthetic Text GenerationCode0
Data-efficient Event Camera Pre-training via Disentangled Masked Modeling—0
Direct Alignment of Draft Model for Speculative Decoding with Chat-Fine-Tuned LLMs—0
A Cognitive-Based Trajectory Prediction Approach for Autonomous DrivingCode2
Weakly Supervised Monocular 3D Detection with a Single-View Image—0
MIKO: Multimodal Intention Knowledge Distillation from Large Language Models for Social-Media Commonsense Discovery—0
A Lightweight Low-Light Image Enhancement Network via Channel Prior and Gamma Correction—0
3MVRD: Multimodal Multi-task Multi-teacher Visually-Rich Form Document UnderstandingCode0
Sunshine to Rainstorm: Cross-Weather Knowledge Distillation for Robust 3D Object DetectionCode1
Gradient Reweighting: Towards Imbalanced Class-Incremental Learning—0
Sinkhorn Distance Minimization for Knowledge DistillationCode2
PromptMM: Multi-Modal Knowledge Distillation for Recommendation with Prompt-TuningCode2
Structural Teacher-Student Normality Learning for Multi-Class Anomaly Detection and Localization—0
SDDGR: Stable Diffusion-based Deep Generative Replay for Class Incremental Object Detection—0
MCF-VC: Mitigate Catastrophic Forgetting in Class-Incremental Learning for Multimodal Video Captioning—0
DTCM: Deep Transformer Capsule Mutual Distillation for Multivariate Time Series Classification—0
m2mKD: Module-to-Module Knowledge Distillation for Modular TransformersCode0
SKILL: Similarity-aware Knowledge distILLation for Speech Self-Supervised Learning—0
LLM-based Privacy Data Augmentation Guided by Knowledge Distillation with a Distribution Tutor for Medical Text Classification—0
LLM Inference Unveiled: Survey and Roofline Model InsightsCode4
Distilling Adversarial Robustness Using Heterogeneous Teachers—0
Practical Insights into Knowledge Distillation for Pre-Trained Models—0
TIE-KD: Teacher-Independent and Explainable Knowledge Distillation for Monocular Depth EstimationCode0
Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off—0
Enhancing Systematic Decompositional Natural Language Inference Using Informal Logic—0
PaCKD: Pattern-Clustered Knowledge Distillation for Compressing Memory Access Prediction ModelsCode0
Wisdom of Committee: Distilling from Foundation Model to Specialized Application Model—0
In-Distribution Consistency Regularization Improves the Generalization of Quantization-Aware Training—0
Unsupervised Text Style Transfer via LLMs and Attention Masking with Multi-way Interactions—0
PIRB: A Comprehensive Benchmark of Polish Dense and Hybrid Text Retrieval Methods—0
PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt TuningCode1
FGAD: Self-boosted Knowledge Distillation for An Effective Federated Graph Anomaly Detection Framework—0
A Survey on Knowledge Distillation of Large Language ModelsCode5
Improve Cross-Architecture Generalization on Dataset DistillationCode1
ELAD: Explanation-Guided Large Language Models Active Distillation—0
Induced Model Matching: How Restricted Models Can Help Larger OnesCode0
Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMsCode4
Revisiting Knowledge Distillation for Autoregressive Language ModelsCode0
On the Byzantine-Resilience of Distillation-Based Federated LearningCode0
Teacher as a Lenient Expert: Teacher-Agnostic Data-Free Knowledge DistillationCode0
GraphKD: Exploring Knowledge Distillation Towards Document Object Detection with Structured Graph CreationCode1
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