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 101–150 of 4240 papers

TitleStatusHype
Accessing Vision Foundation Models at ImageNet-level CostsCode2
Scale Decoupled DistillationCode2
DOT: A Distillation-Oriented TrainerCode2
Distillation-Supervised Convolutional Low-Rank Adaptation for Efficient Image Super-ResolutionCode2
Social4Rec: Distilling User Preference from Social Graph for Video Recommendation in TencentCode2
Solving ImageNet: a Unified Scheme for Training any Backbone to Top ResultsCode2
Structural Entropy Guided Agent for Detecting and Repairing Knowledge Deficiencies in LLMsCode2
CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-TuningCode2
TextBrewer: An Open-Source Knowledge Distillation Toolkit for Natural Language ProcessingCode2
Tiny Object Tracking: A Large-scale Dataset and A BaselineCode2
Dual-Space Knowledge Distillation for Large Language ModelsCode2
Decoupled Knowledge DistillationCode2
VkD: Improving Knowledge Distillation using Orthogonal ProjectionsCode2
Wasserstein Distance Rivals Kullback-Leibler Divergence for Knowledge DistillationCode2
Scalable Zero-shot Entity Linking with Dense Entity RetrievalCode2
MiniLLM: Knowledge Distillation of Large Language ModelsCode2
BiM-VFI: directional Motion Field-Guided Frame Interpolation for Video with Non-uniform MotionsCode2
JL1-CD: A New Benchmark for Remote Sensing Change Detection and a Robust Multi-Teacher Knowledge Distillation FrameworkCode2
A Cognitive-Based Trajectory Prediction Approach for Autonomous DrivingCode2
2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point CloudsCode2
Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel BaselineCode2
Event Stream-based Visual Object Tracking: HDETrack V2 and A High-Definition BenchmarkCode2
ConDistFL: Conditional Distillation for Federated Learning from Partially Annotated DataCode2
Diffusion Time-step Curriculum for One Image to 3D GenerationCode2
Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio ModelsCode2
LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference OptimizationCode2
Progressive Knowledge Distillation Of Stable Diffusion XL Using Layer Level LossCode2
OBSeg: Accurate and Fast Instance Segmentation Framework Using Segmentation Foundation Models with Oriented Bounding Box PromptsCode2
Cross-Image Relational Knowledge Distillation for Semantic SegmentationCode2
A Deep Knowledge Distillation framework for EEG assisted enhancement of single-lead ECG based sleep stagingCode1
Baby Llama: knowledge distillation from an ensemble of teachers trained on a small dataset with no performance penaltyCode1
Avatar Knowledge Distillation: Self-ensemble Teacher Paradigm with UncertaintyCode1
Backdoor Attacks on Self-Supervised LearningCode1
Collaborative Distillation for Ultra-Resolution Universal Style TransferCode1
COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using TransformersCode1
Model LEGO: Creating Models Like Disassembling and Assembling Building BlocksCode1
Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual LearningCode1
Coaching a Teachable StudentCode1
Backdoor Cleansing with Unlabeled DataCode1
Communication-Efficient Federated Learning through Adaptive Weight Clustering and Server-Side DistillationCode1
Cloud Object Detector Adaptation by Integrating Different Source KnowledgeCode1
AutoGAN-Distiller: Searching to Compress Generative Adversarial NetworksCode1
CLRKDNet: Speeding up Lane Detection with Knowledge DistillationCode1
Understanding the Role of the Projector in Knowledge DistillationCode1
Adaptive Multi-Teacher Multi-level Knowledge DistillationCode1
FocusNet: Classifying Better by Focusing on Confusing ClassesCode1
CMDFusion: Bidirectional Fusion Network with Cross-modality Knowledge Distillation for LIDAR Semantic SegmentationCode1
Adaptive Multi-Teacher Knowledge Distillation with Meta-LearningCode1
CLIP-KD: An Empirical Study of CLIP Model DistillationCode1
CLIP model is an Efficient Continual LearnerCode1
Show:102550
← PrevPage 3 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