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
Focal Loss for Dense Object DetectionCode2
A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and FutureCode2
Sinkhorn Distance Minimization for Knowledge DistillationCode2
Social4Rec: Distilling User Preference from Social Graph for Video Recommendation in TencentCode2
SSDA-YOLO: Semi-supervised Domain Adaptive YOLO for Cross-Domain Object DetectionCode2
Structural Entropy Guided Agent for Detecting and Repairing Knowledge Deficiencies in LLMsCode2
Rethinking Transformer-Based Blind-Spot Network for Self-Supervised Image DenoisingCode2
TextBrewer: An Open-Source Knowledge Distillation Toolkit for Natural Language ProcessingCode2
Distillation-Supervised Convolutional Low-Rank Adaptation for Efficient Image Super-ResolutionCode2
Distillation-Free One-Step Diffusion for Real-World Image Super-ResolutionCode2
VkD: Improving Knowledge Distillation using Orthogonal ProjectionsCode2
Wasserstein Distance Rivals Kullback-Leibler Divergence for Knowledge DistillationCode2
DOT: A Distillation-Oriented TrainerCode2
Scalable Zero-shot Entity Linking with Dense Entity RetrievalCode2
Knowledge distillation: A good teacher is patient and consistentCode2
JL1-CD: A New Benchmark for Remote Sensing Change Detection and a Robust Multi-Teacher Knowledge Distillation FrameworkCode2
Data-Free Knowledge Distillation for Deep Neural NetworksCode2
2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point CloudsCode2
Event Stream-based Visual Object Tracking: HDETrack V2 and A High-Definition BenchmarkCode2
ESP-MedSAM: Efficient Self-Prompting SAM for Universal Domain-Generalized Medical Image SegmentationCode2
ConDistFL: Conditional Distillation for Federated Learning from Partially Annotated DataCode2
Decoupled Knowledge DistillationCode2
Dual-Space Knowledge Distillation for Large Language ModelsCode2
From Instance Training to Instruction Learning: Task Adapters Generation from InstructionsCode2
LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPSCode2
OBSeg: Accurate and Fast Instance Segmentation Framework Using Segmentation Foundation Models with Oriented Bounding Box PromptsCode2
Progressive Knowledge Distillation Of Stable Diffusion XL Using Layer Level LossCode2
A Deep Knowledge Distillation framework for EEG assisted enhancement of single-lead ECG based sleep stagingCode1
Collaborative Distillation for Ultra-Resolution Universal Style TransferCode1
AutoGAN-Distiller: Searching to Compress Generative Adversarial NetworksCode1
Model LEGO: Creating Models Like Disassembling and Assembling Building BlocksCode1
Coaching a Teachable StudentCode1
COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using TransformersCode1
CMDFusion: Bidirectional Fusion Network with Cross-modality Knowledge Distillation for LIDAR Semantic SegmentationCode1
Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual LearningCode1
CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual DistillationCode1
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?Code1
CLRKDNet: Speeding up Lane Detection with Knowledge DistillationCode1
Communication-Efficient Federated Learning through Adaptive Weight Clustering and Server-Side DistillationCode1
CLIP model is an Efficient Continual LearnerCode1
Augmentation-Free Dense Contrastive Knowledge Distillation for Efficient Semantic SegmentationCode1
CL-LoRA: Continual Low-Rank Adaptation for Rehearsal-Free Class-Incremental LearningCode1
Understanding the Role of the Projector in Knowledge DistillationCode1
Adaptive Multi-Teacher Multi-level Knowledge DistillationCode1
FocusNet: Classifying Better by Focusing on Confusing ClassesCode1
Adaptive Multi-Teacher Knowledge Distillation with Meta-LearningCode1
Audio Embeddings as Teachers for Music ClassificationCode1
Audio-Visual Representation Learning via Knowledge Distillation from Speech Foundation ModelsCode1
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