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 1–50 of 4240 papers

TitleStatusHype
O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?Code7
Awesome Multi-modal Object TrackingCode5
A Survey on Knowledge Distillation of Large Language ModelsCode5
MobileSAMv2: Faster Segment Anything to EverythingCode5
AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-TimeCode5
SAMPart3D: Segment Any Part in 3D ObjectsCode4
LLM Inference Unveiled: Survey and Roofline Model InsightsCode4
Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMsCode4
BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-DistillationCode4
Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo LabellingCode4
Effective Whole-body Pose Estimation with Two-stages DistillationCode4
Vision-Language Models for Vision Tasks: A SurveyCode4
Efficient and Generalizable Speaker Diarization via Structured Pruning of Self-Supervised ModelsCode3
Efficient Reasoning Models: A SurveyCode3
A Survey on Inference Optimization Techniques for Mixture of Experts ModelsCode3
LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge DistillationCode3
Compact Language Models via Pruning and Knowledge DistillationCode3
Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-DistillationCode3
Recurrent Drafter for Fast Speculative Decoding in Large Language ModelsCode3
PromptKD: Unsupervised Prompt Distillation for Vision-Language ModelsCode3
Logit Standardization in Knowledge DistillationCode3
DistiLLM: Towards Streamlined Distillation for Large Language ModelsCode3
Generalized Robot 3D Vision-Language Model with Fast Rendering and Pre-Training Vision-Language AlignmentCode3
ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-SpeechCode3
CMKD: CNN/Transformer-Based Cross-Model Knowledge Distillation for Audio ClassificationCode3
N-LTP: An Open-source Neural Language Technology Platform for ChineseCode3
Semi-Supervised Speech Recognition via Local Prior MatchingCode3
Structural Entropy Guided Agent for Detecting and Repairing Knowledge Deficiencies in LLMsCode2
Efficient Multivariate Time Series Forecasting via Calibrated Language Models with Privileged Knowledge DistillationCode2
Distillation-Supervised Convolutional Low-Rank Adaptation for Efficient Image Super-ResolutionCode2
Learning Occlusion-Robust Vision Transformers for Real-Time UAV TrackingCode2
SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-ImprovementCode2
Scaling Down Text Encoders of Text-to-Image Diffusion ModelsCode2
A Comprehensive Survey on Knowledge DistillationCode2
LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference OptimizationCode2
JL1-CD: A New Benchmark for Remote Sensing Change Detection and a Robust Multi-Teacher Knowledge Distillation FrameworkCode2
Event Stream-based Visual Object Tracking: HDETrack V2 and A High-Definition BenchmarkCode2
LightGNN: Simple Graph Neural Network for RecommendationCode2
Optimizing Edge AI: A Comprehensive Survey on Data, Model, and System StrategiesCode2
Learning an Adaptive and View-Invariant Vision Transformer for Real-Time UAV TrackingCode2
Learnable Prompting SAM-induced Knowledge Distillation for Semi-supervised Medical Image SegmentationCode2
BiM-VFI: directional Motion Field-Guided Frame Interpolation for Video with Non-uniform MotionsCode2
Wasserstein Distance Rivals Kullback-Leibler Divergence for Knowledge DistillationCode2
BiomedCoOp: Learning to Prompt for Biomedical Vision-Language ModelsCode2
ScaleKD: Strong Vision Transformers Could Be Excellent TeachersCode2
MiniPLM: Knowledge Distillation for Pre-Training Language ModelsCode2
Distillation-Free One-Step Diffusion for Real-World Image Super-ResolutionCode2
Learning from Committee: Reasoning Distillation from a Mixture of Teachers with Peer-ReviewCode2
Ruri: Japanese General Text EmbeddingsCode2
Towards A Generalizable Pathology Foundation Model via Unified Knowledge DistillationCode2
Show:102550
← PrevPage 1 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