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 1601–1650 of 4240 papers

TitleStatusHype
Fair Feature Importance Scores for Interpreting Tree-Based Methods and Surrogates—0
LumiNet: The Bright Side of Perceptual Knowledge DistillationCode1
DED: Diagnostic Evidence Distillation for acne severity grading on face imagesCode0
Improving Knowledge Distillation with Teacher's Explanation—0
I^2KD-SLU: An Intra-Inter Knowledge Distillation Framework for Zero-Shot Cross-Lingual Spoken Language Understanding—0
Heterogeneous Federated Learning Using Knowledge Codistillation—0
Talking Models: Distill Pre-trained Knowledge to Downstream Models via Interactive Communication—0
SEA: Sparse Linear Attention with Estimated Attention MaskCode1
Can a student Large Language Model perform as well as it's teacher?—0
Learnable Cross-modal Knowledge Distillation for Multi-modal Learning with Missing Modality—0
KGEx: Explaining Knowledge Graph Embeddings via Subgraph Sampling and Knowledge Distillation—0
Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models—0
Towards Fixing Clever-Hans Predictors with Counterfactual Knowledge Distillation—0
Distilling Influences to Mitigate Prediction Churn in Graph Neural NetworksCode0
Adaptive Decoupled Pose Knowledge DistillationCode0
NAYER: Noisy Layer Data Generation for Efficient and Effective Data-free Knowledge DistillationCode1
Distilling Inductive Bias: Knowledge Distillation Beyond Model Compression—0
Towards Few-Call Model Stealing via Active Self-Paced Knowledge Distillation and Diffusion-Based Image Generation—0
Promoting Generalized Cross-lingual Question Answering in Few-resource Scenarios via Self-knowledge DistillationCode0
An Enhanced Low-Resolution Image Recognition Method for Traffic Environments—0
Distill to Delete: Unlearning in Graph Networks with Knowledge Distillation—0
Distilling ODE Solvers of Diffusion Models into Smaller Steps—0
Inherit with Distillation and Evolve with Contrast: Exploring Class Incremental Semantic Segmentation Without Exemplar Memory—0
DualVC 2: Dynamic Masked Convolution for Unified Streaming and Non-Streaming Voice Conversion—0
VideoAdviser: Video Knowledge Distillation for Multimodal Transfer Learning—0
Cold & Warm Net: Addressing Cold-Start Users in Recommender Systems—0
Contrastive Continual Multi-view Clustering with Filtered Structural Fusion—0
Learning Using Generated Privileged Information by Text-to-Image Diffusion Models—0
Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel BaselineCode2
Noise-Tolerant Few-Shot Unsupervised Adapter for Vision-Language Models—0
DONNAv2 -- Lightweight Neural Architecture Search for Vision tasks—0
ADU-Depth: Attention-based Distillation with Uncertainty Modeling for Depth Estimation—0
DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge DistillationCode1
Unsupervised 3D Perception with 2D Vision-Language Distillation for Autonomous Driving—0
Data Upcycling Knowledge Distillation for Image Super-ResolutionCode0
DFRD: Data-Free Robustness Distillation for Heterogeneous Federated Learning—0
Multivariate Prototype Representation for Domain-Generalized Incremental Learning—0
Poster: Self-Supervised Quantization-Aware Knowledge Distillation—0
VIC-KD: Variance-Invariance-Covariance Knowledge Distillation to Make Keyword Spotting More Robust Against Adversarial Attacks—0
Triple-View Knowledge Distillation for Semi-Supervised Semantic Segmentation—0
Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training—0
Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training—0
Elevating Skeleton-Based Action Recognition with Efficient Multi-Modality Self-SupervisionCode0
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language GuidanceCode1
EPTQ: Enhanced Post-Training Quantization via Hessian-guided Network-wise OptimizationCode2
Dense 2D-3D Indoor Prediction with Sound via Aligned Cross-Modal DistillationCode0
Language-Oriented Communication with Semantic Coding and Knowledge Distillation for Text-to-Image Generation—0
Weight Averaging Improves Knowledge Distillation under Domain ShiftCode1
Incorporating Ultrasound Tongue Images for Audio-Visual Speech Enhancement—0
Improving CLIP Robustness with Knowledge Distillation and Self-Training—0
Show:102550
← PrevPage 33 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