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 3901–3950 of 4240 papers

TitleStatusHype
Label Semantic Knowledge Distillation for Unbiased Scene Graph Generation—0
LadaBERT: Lightweight Adaptation of BERT through Hybrid Model Compression—0
LaDiMo: Layer-wise Distillation Inspired MoEfier—0
LAKD-Activation Mapping Distillation Based on Local Learning—0
LAMeTA: Intent-Aware Agentic Network Optimization via a Large AI Model-Empowered Two-Stage Approach—0
Language Graph Distillation for Low-Resource Machine Translation—0
Language Modelling via Learning to Rank—0
Language-Oriented Communication with Semantic Coding and Knowledge Distillation for Text-to-Image Generation—0
LAPTOP-Diff: Layer Pruning and Normalized Distillation for Compressing Diffusion Models—0
Just CHOP: Embarrassingly Simple LLM Compression—0
Large Language Model Guided Knowledge Distillation for Time Series Anomaly Detection—0
Large Language Model Meets Graph Neural Network in Knowledge Distillation—0
Large Model for Small Data: Foundation Model for Cross-Modal RF Human Activity Recognition—0
Large-Scale Generative Data-Free Distillation—0
LaSNN: Layer-wise ANN-to-SNN Distillation for Effective and Efficient Training in Deep Spiking Neural Networks—0
Layer Attack Unlearning: Fast and Accurate Machine Unlearning via Layer Level Attack and Knowledge Distillation—0
LayerCollapse: Adaptive compression of neural networks—0
Layer Importance for Mathematical Reasoning is Forged in Pre-Training and Invariant after Post-Training—0
Layerwise Bregman Representation Learning with Applications to Knowledge Distillation—0
Noisy Data Meets Privacy: Training Local Models with Post-Processed Remote Queries—0
LEAD: Liberal Feature-based Distillation for Dense Retrieval—0
LEALLA: Learning Lightweight Language-agnostic Sentence Embeddings with Knowledge Distillation—0
Learnable Cross-modal Knowledge Distillation for Multi-modal Learning with Missing Modality—0
Learn from Balance: Rectifying Knowledge Transfer for Long-Tailed Scenarios—0
Learn From the Past: Experience Ensemble Knowledge Distillation—0
Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detection—0
Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection—0
Learning Bayesian Sparse Networks with Full Experience Replay for Continual Learning—0
Learning by Distillation: A Self-Supervised Learning Framework for Optical Flow Estimation—0
Learning Cross-Lingual IR from an English Retriever—0
Diverse Knowledge Distillation (DKD): A Solution for Improving The Robustness of Ensemble Models Against Adversarial Attacks—0
Learning Efficient Image Super-Resolution Networks via Structure-Regularized Pruning—0
Learning Efficient Object Detection Models with Knowledge Distillation—0
Learning from a Lightweight Teacher for Efficient Knowledge Distillation—0
Learning From Biased Soft Labels—0
Learning from deep model via exploring local targets—0
Learning from Imperfect Data: Towards Efficient Knowledge Distillation of Autoregressive Language Models for Text-to-SQL—0
Learning from Matured Dumb Teacher for Fine Generalization—0
Learning Human-Human Interactions in Images from Weak Textual Supervision—0
MixMix: All You Need for Data-Free Compression Are Feature and Data Mixing—0
Learning Interpretation with Explainable Knowledge Distillation—0
Learning Knowledge Representation with Meta Knowledge Distillation for Single Image Super-Resolution—0
Learning Lightweight Object Detectors via Multi-Teacher Progressive Distillation—0
Learning Lightweight Pedestrian Detector with Hierarchical Knowledge Distillation—0
Learning Modality-agnostic Representation for Semantic Segmentation from Any Modalities—0
Learning Student-Friendly Teacher Networks for Knowledge Distillation—0
Learning Student Networks via Feature Embedding—0
Learning Task-Agnostic Embedding of Multiple Black-Box Experts for Multi-Task Model Fusion—0
Learning the Wrong Lessons: Inserting Trojans During Knowledge Distillation—0
Learning Through Guidance: Knowledge Distillation for Endoscopic Image Classification—0
Show:102550
← PrevPage 79 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