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 251–300 of 4240 papers

TitleStatusHype
Training Domain Draft Models for Speculative Decoding: Best Practices and Insights—0
Distilling Knowledge into Quantum Vision Transformers for Biomedical Image Classification—0
PTMs-TSCIL Pre-Trained Models Based Class-Incremental Learning—0
Task-Specific Knowledge Distillation from the Vision Foundation Model for Enhanced Medical Image Segmentation—0
ADROIT: A Self-Supervised Framework for Learning Robust Representations for Active Learning—0
CoT-Drive: Efficient Motion Forecasting for Autonomous Driving with LLMs and Chain-of-Thought Prompting—0
Small Vision-Language Models: A Survey on Compact Architectures and Techniques—0
Causality Enhanced Origin-Destination Flow Prediction in Data-Scarce Cities—0
HFedCKD: Toward Robust Heterogeneous Federated Learning via Data-free Knowledge Distillation and Two-way Contrast—0
Asymmetric Decision-Making in Online Knowledge Distillation:Unifying Consensus and Divergence—0
Improving SAM for Camouflaged Object Detection via Dual Stream Adapters—0
ACAM-KD: Adaptive and Cooperative Attention Masking for Knowledge Distillation—0
Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental LearningCode1
Spatial Distillation based Distribution Alignment (SDDA) for Cross-Headset EEG ClassificationCode1
No Forgetting Learning: Memory-free Continual Learning—0
Lightweight Embedded FPGA Deployment of Learned Image Compression with Knowledge Distillation and Hybrid Quantization—0
Self-Supervised Z-Slice Augmentation for 3D Bio-Imaging via Knowledge DistillationCode0
Temporal Separation with Entropy Regularization for Knowledge Distillation in Spiking Neural Networks—0
Rapid Bone Scintigraphy Enhancement via Semantic Prior Distillation from Segment Anything Model—0
Mamba base PKD for efficient knowledge compression—0
DILEMMA: Joint LLM Quantization and Distributed LLM Inference Over Edge Computing Systems—0
VRM: Knowledge Distillation via Virtual Relation Matching—0
Investigating and Enhancing Vision-Audio Capability in Omnimodal Large Language Models—0
SEKI: Self-Evolution and Knowledge Inspiration based Neural Architecture Search via Large Language Models—0
Granite Embedding Models—0
XCOMPS: A Multilingual Benchmark of Conceptual Minimal Pairs—0
Lightweight Contrastive Distilled Hashing for Online Cross-modal Retrieval—0
Beyond the Tip of Efficiency: Uncovering the Submerged Threats of Jailbreak Attacks in Small Language Models—0
Winning Big with Small Models: Knowledge Distillation vs. Self-Training for Reducing Hallucination in QA Agents—0
AfroXLMR-Comet: Multilingual Knowledge Distillation with Attention Matching for Low-Resource languages—0
Advantage-Guided Distillation for Preference Alignment in Small Language ModelsCode1
From underwater to aerial: a novel multi-scale knowledge distillation approach for coral reef monitoringCode0
Knowledge Distillation with Training Wheels—0
CLIMB-3D: Continual Learning for Imbalanced 3D Instance SegmentationCode0
PQDAST: Depth-Aware Arbitrary Style Transfer for Games via Perceptual Quality-Guided Distillation—0
A Transformer-in-Transformer Network Utilizing Knowledge Distillation for Image Recognition—0
Implicit Word Reordering with Knowledge Distillation for Cross-Lingual Dependency Parsing—0
CoT2Align: Cross-Chain of Thought Distillation via Optimal Transport Alignment for Language Models with Different Tokenizers—0
Improving the Transferability of Adversarial Examples by Inverse Knowledge Distillation—0
EDocNet: Efficient Datasheet Layout Analysis Based on Focus and Global Knowledge Distillation—0
Scaling Sparse and Dense Retrieval in Decoder-Only LLMsCode1
PPC-GPT: Federated Task-Specific Compression of Large Language Models via Pruning and Chain-of-Thought Distillation—0
A Knowledge Distillation-Based Approach to Enhance Transparency of Classifier ModelsCode0
TimeDistill: Efficient Long-Term Time Series Forecasting with MLP via Cross-Architecture Distillation—0
Self-supervised Monocular Depth Estimation Robust to Reflective Surface Leveraged by Triplet Mining—0
Efficient AI in Practice: Training and Deployment of Efficient LLMs for Industry Applications—0
Modifying Final Splits of Classification Tree for Fine-tuning Subpopulation Target in Policy Making—0
Vision Foundation Models in Medical Image Analysis: Advances and Challenges—0
Designing Parameter and Compute Efficient Diffusion Transformers using Distillation—0
Dynamic Activation with Knowledge Distillation for Energy-Efficient Spiking NN Ensembles—0
Show:102550
← PrevPage 6 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