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 3051–3100 of 4240 papers

TitleStatusHype
Knowledge Distillation via Weighted Ensemble of Teaching Assistants—0
Conformer with dual-mode chunked attention for joint online and offline ASR—0
Knowledge Distillation for Oriented Object Detection on Aerial Images—0
Revisiting Self-Distillation—0
Multi scale Feature Extraction and Fusion for Online Knowledge Distillation—0
FreeKD: Free-direction Knowledge Distillation for Graph Neural Networks—0
Toward Student-Oriented Teacher Network Training For Knowledge Distillation—0
FreeTransfer-X: Safe and Label-Free Cross-Lingual Transfer from Off-the-Shelf Models—0
Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge DistillationCode0
Robust Distillation for Worst-class Performance—0
Federated Bayesian Neural Regression: A Scalable Global Federated Gaussian Process—0
Reducing Capacity Gap in Knowledge Distillation with Review Mechanism for Crowd CountingCode0
SDQ: Stochastic Differentiable Quantization with Mixed Precision—0
Knowledge Distillation Decision Tree for Unravelling Black-box Machine Learning Models—0
Narrowing the Coordinate-frame Gap in Behavior Prediction Models: Distillation for Efficient and Accurate Scene-centric Motion Forecasting—0
cViL: Cross-Lingual Training of Vision-Language Models using Knowledge DistillationCode0
Self-Knowledge Distillation based Self-Supervised Learning for Covid-19 Detection from Chest X-Ray Images—0
Reconsidering Learning Objectives in Unbiased Recommendation with Unobserved Confounders—0
Confidence-aware Self-Semantic Distillation on Knowledge Graph Embedding—0
Evaluation-oriented Knowledge Distillation for Deep Face Recognition—0
Lip-Listening: Mixing Senses to Understand Lips using Cross Modality Knowledge Distillation for Word-Based Models—0
Point-to-Voxel Knowledge Distillation for LiDAR Semantic SegmentationCode0
Vanilla Feature Distillation for Improving the Accuracy-Robustness Trade-Off in Adversarial Training—0
Extreme Compression for Pre-trained Transformers Made Simple and Efficient—0
Guided Deep Metric Learning—0
3D-Augmented Contrastive Knowledge Distillation for Image-based Object Pose Estimation—0
ORC: Network Group-based Knowledge Distillation using Online Role ChangeCode0
Generalized Supervised Contrastive Learning—0
Detecting Optimism in Tweets using Knowledge Distillation and Linguistic Analysis of Optimism—0
Searching for COMETINHO: The Little Metric That Could—0
What Knowledge Gets Distilled in Knowledge Distillation?—0
VFed-SSD: Towards Practical Vertical Federated Advertising—0
Spectral Maps for Learning on Subgraphs—0
Knowledge Distillation for 6D Pose Estimation by Aligning Distributions of Local Predictions—0
A General Multiple Data Augmentation Based Framework for Training Deep Neural Networks—0
MiniDisc: Minimal Distillation Schedule for Language Model CompressionCode0
One Reference Is Not Enough: Diverse Distillation with Reference Selection for Non-Autoregressive TranslationCode0
Parameter-Efficient and Student-Friendly Knowledge Distillation—0
Region-aware Knowledge Distillation for Efficient Image-to-Image Translation—0
Do we need Label Regularization to Fine-tune Pre-trained Language Models?—0
DFM: Dialogue Foundation Model for Universal Large-Scale Dialogue-Oriented Task Learning—0
CDFKD-MFS: Collaborative Data-free Knowledge Distillation via Multi-level Feature SharingCode0
LILA-BOTI : Leveraging Isolated Letter Accumulations By Ordering Teacher Insights for Bangla Handwriting RecognitionCode0
Aligning Logits Generatively for Principled Black-Box Knowledge DistillationCode0
InDistill: Information flow-preserving knowledge distillation for model compressionCode0
Simple Regularisation for Uncertainty-Aware Knowledge Distillation—0
ERNIE-Search: Bridging Cross-Encoder with Dual-Encoder via Self On-the-fly Distillation for Dense Passage Retrieval—0
Prompting to Distill: Boosting Data-Free Knowledge Distillation via Reinforced Prompt—0
Chemical transformer compression for accelerating both training and inference of molecular modelingCode0
Not to Overfit or Underfit the Source Domains? An Empirical Study of Domain Generalization in Question Answering—0
Show:102550
← PrevPage 62 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