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 1401–1450 of 4240 papers

TitleStatusHype
Point Segment and Count: A Generalized Framework for Object CountingCode2
FCS: Feature Calibration and Separation for Non-Exemplar Class Incremental LearningCode1
DIOD: Self-Distillation Meets Object DiscoveryCode1
KD-DETR: Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling—0
Scene-adaptive and Region-aware Multi-modal Prompt for Open Vocabulary Object Detection—0
Uncertainty-Guided Never-Ending Learning to Drive—0
Robust Distillation via Untargeted and Targeted Intermediate Adversarial Samples—0
Scaled Decoupled DistillationCode2
CaKDP: Category-aware Knowledge Distillation and Pruning Framework for Lightweight 3D Object DetectionCode1
Building Vision-Language Models on Solid Foundations with Masked Distillation—0
LiSA: LiDAR Localization with Semantic AwarenessCode2
IQ-VFI: Implicit Quadratic Motion Estimation for Video Frame Interpolation—0
VkD: Improving Knowledge Distillation using Orthogonal ProjectionsCode2
Distribution-aware Knowledge Prototyping for Non-exemplar Lifelong Person Re-identificationCode1
Distilling CLIP with Dual Guidance for Learning Discriminative Human Body Shape Representation—0
C2KD: Bridging the Modality Gap for Cross-Modal Knowledge Distillation—0
Curriculum-scheduled Knowledge Distillation from Multiple Pre-trained Teachers for Multi-domain Sequential RecommendationCode0
SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPCCode0
Compressing Deep Image Super-resolution Models—0
Explainability-Driven Leaf Disease Classification Using Adversarial Training and Knowledge Distillation—0
ClST: A Convolutional Transformer Framework for Automatic Modulation Recognition by Knowledge Distillation—0
FerKD: Surgical Label Adaptation for Efficient DistillationCode1
Temporal Knowledge Distillation for Time-Sensitive Financial Services Applications—0
FedSDD: Scalable and Diversity-enhanced Distillation for Model Aggregation in Federated Learning—0
Layer Attack Unlearning: Fast and Accurate Machine Unlearning via Layer Level Attack and Knowledge Distillation—0
X Modality Assisting RGBT Object Tracking—0
Dynamic Sub-graph Distillation for Robust Semi-supervised Continual LearningCode0
Group Multi-View Transformer for 3D Shape Analysis with Spatial EncodingCode0
AdapterDistillation: Non-Destructive Task Composition with Knowledge Distillation—0
Cloud-Device Collaborative Learning for Multimodal Large Language Models—0
Knowledge Distillation of LLM for Automatic Scoring of Science Education Assessments—0
Revisiting Knowledge Distillation under Distribution ShiftCode0
Less or More From Teacher: Exploiting Trilateral Geometry For Knowledge Distillation—0
Compressing Image-to-Image Translation GANs Using Local Density Structures on Their Learned Manifold—0
TinySAM: Pushing the Envelope for Efficient Segment Anything ModelCode2
How to Prune Your Language Model: Recovering Accuracy on the "Sparsity May Cry'' Benchmark—0
Object Attribute Matters in Visual Question AnsweringCode0
DSFormer: Effective Compression of Text-Transformers by Dense-Sparse Weight Factorization—0
StableKD: Breaking Inter-block Optimization Entanglement for Stable Knowledge DistillationCode0
Fine-Grained Knowledge Selection and Restoration for Non-Exemplar Class Incremental LearningCode0
Federated Learning with Extremely Noisy Clients via Negative DistillationCode1
Expediting Contrastive Language-Image Pretraining via Self-distilled Encoders—0
Distilling Autoregressive Models to Obtain High-Performance Non-Autoregressive Solvers for Vehicle Routing Problems with Faster Inference SpeedCode1
RadOcc: Learning Cross-Modality Occupancy Knowledge through Rendering Assisted Distillation—0
Decoupled Knowledge with Ensemble Learning for Online DistillationCode0
Your Student is Better Than Expected: Adaptive Teacher-Student Collaboration for Text-Conditional Diffusion ModelsCode1
DistilVPR: Cross-Modal Knowledge Distillation for Visual Place RecognitionCode1
Mixed Distillation Helps Smaller Language Model Better Reasoning—0
Symmetrical Bidirectional Knowledge Alignment for Zero-Shot Sketch-Based Image RetrievalCode0
Simple Image-level Classification Improves Open-vocabulary Object DetectionCode1
Show:102550
← PrevPage 29 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