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
Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation—0
WAVE: Weight Template for Adaptive Initialization of Variable-sized Models—0
Weakly Supervised Cross-lingual Semantic Relation Classification via Knowledge Distillation—0
Weakly Supervised Dense Video Captioning via Jointly Usage of Knowledge Distillation and Cross-modal Matching—0
Weakly-Supervised Domain Adaptation of Deep Regression Trackers via Reinforced Knowledge Distillation—0
Weakly-supervised HOI Detection via Prior-guided Bi-level Representation Learning—0
Weakly Supervised Monocular 3D Detection with a Single-View Image—0
Weakly Supervised Semantic Segmentation via Alternative Self-Dual Teaching—0
Weak-to-Strong Backdoor Attack for Large Language Models—0
Wearable Accelerometer Foundation Models for Health via Knowledge Distillation—0
WebChild 2.0 : Fine-Grained Commonsense Knowledge Distillation—0
Web Content Filtering through knowledge distillation of Large Language Models—0
WebUOT-1M: Advancing Deep Underwater Object Tracking with A Million-Scale Benchmark—0
WeChat Neural Machine Translation Systems for WMT20—0
WeChat Neural Machine Translation Systems for WMT21—0
WeClick: Weakly-Supervised Video Semantic Segmentation with Click Annotations—0
Weight Averaging: A Simple Yet Effective Method to Overcome Catastrophic Forgetting in Automatic Speech Recognition—0
Weight Decay Scheduling and Knowledge Distillation for Active Learning—0
Weight Distillation: Transferring the Knowledge in Neural Network Parameters—0
Weighted KL-Divergence for Document Ranking Model Refinement—0
Weight Squeezing: Reparameterization for Compression and Fast Inference—0
Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding—0
What do larger image classifiers memorise?—0
What Happens When Small Is Made Smaller? Exploring the Impact of Compression on Small Data Pretrained Language Models—0
What is Left After Distillation? How Knowledge Transfer Impacts Fairness and Bias—0
What is Lost in Knowledge Distillation?—0
What Knowledge Gets Distilled in Knowledge Distillation?—0
What Makes a Good Dataset for Knowledge Distillation?—0
When Chosen Wisely, More Data Is What You Need: A Universal Sample-Efficient Strategy For Data Augmentation—0
When Gradient Descent Meets Derivative-Free Optimization: A Match Made in Black-Box Scenario—0
Which Student is Best? A Comprehensive Knowledge Distillation Exam for Task-Specific BERT Models—0
DQ-Whisper: Joint Distillation and Quantization for Efficient Multilingual Speech Recognition—0
Whole-Slide Mitosis Detection in H&E Breast Histology Using PHH3 as a Reference to Train Distilled Stain-Invariant Convolutional Networks—0
Why distillation helps: a statistical perspective—0
Why Knowledge Distillation Amplifies Gender Bias and How to Mitigate from the Perspective of DistilBERT—0
Why Knowledge Distillation Works in Generative Models: A Minimal Working Explanation—0
Winning Big with Small Models: Knowledge Distillation vs. Self-Training for Reducing Hallucination in QA Agents—0
Win the Lottery Ticket via Fourier Analysis: Frequencies Guided Network Pruning—0
Wired Perspectives: Multi-View Wire Art Embraces Generative AI—0
Wisdom of Committee: Distilling from Foundation Model to Specialized Application Model—0
WK-Pnet: FM-Based Positioning via Wavelet Packet Decomposition and Knowledge Distillation—0
Word Sense Induction with Knowledge Distillation from BERT—0
X^3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detection—0
X3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detection—0
XCOMPS: A Multilingual Benchmark of Conceptual Minimal Pairs—0
XD: Cross-lingual Knowledge Distillation for Polyglot Sentence Embeddings—0
X-Distill: Improving Self-Supervised Monocular Depth via Cross-Task Distillation—0
Xiaomi's Submissions for IWSLT 2020 Open Domain Translation Task—0
X Modality Assisting RGBT Object Tracking—0
xVLM2Vec: Adapting LVLM-based embedding models to multilinguality using Self-Knowledge Distillation—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