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 2251–2300 of 4240 papers

TitleStatusHype
Boosting Summarization with Normalizing Flows and Aggressive TrainingCode0
Interactive Multi-fidelity Learning for Cost-effective Adaptation of Language Model with Sparse Human Supervision—0
AMLNet: Adversarial Mutual Learning Neural Network for Non-AutoRegressive Multi-Horizon Time Series ForecastingCode0
MUST: A Multilingual Student-Teacher Learning approach for low-resource speech recognition—0
RCKD: Response-Based Cross-Task Knowledge Distillation for Pathological Image Analysis—0
Ever Evolving Evaluator (EV3): Towards Flexible and Reliable Meta-Optimization for Knowledge Distillation—0
ODM3D: Alleviating Foreground Sparsity for Semi-Supervised Monocular 3D Object DetectionCode0
Efficient Object Detection in Optical Remote Sensing Imagery via Attention-based Feature Distillation—0
Discourse Structures Guided Fine-grained Propaganda IdentificationCode0
Towards a Unified Conversational Recommendation System: Multi-task Learning via Contextualized Knowledge DistillationCode0
Multi-label Emotion Analysis in Conversation via Multimodal Knowledge Distillation—0
torchdistill Meets Hugging Face Libraries for Reproducible, Coding-Free Deep Learning Studies: A Case Study on NLP—0
Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained ModelCode0
SonoSAMTrack -- Segment and Track Anything on Ultrasound Images—0
TOP-Training: Target-Oriented Pretraining for Medical Extractive Question AnsweringCode0
Cross-feature Contrastive Loss for Decentralized Deep Learning on Heterogeneous DataCode0
Wakening Past Concepts without Past Data: Class-Incremental Learning from Online Placebos—0
ABKD: Graph Neural Network Compression with Attention-Based Knowledge Distillation—0
MCC-KD: Multi-CoT Consistent Knowledge DistillationCode0
Leveraging Complementary Attention maps in vision transformers for OCT image analysis—0
Data-Free Knowledge Distillation Using Adversarially Perturbed OpenGL Shader Images—0
DistillCSE: Distilled Contrastive Learning for Sentence EmbeddingsCode0
GenDistiller: Distilling Pre-trained Language Models based on Generative Models—0
Enhancing Abstractiveness of Summarization Models through Calibrated Distillation—0
Leveraging Knowledge Distillation for Efficient Deep Reinforcement Learning in Resource-Constrained EnvironmentsCode0
A Comparative Analysis of Task-Agnostic Distillation Methods for Compressing Transformer Language Models—0
Revisiting Multi-modal 3D Semantic Segmentation in Real-world Autonomous Driving—0
DistillSpec: Improving Speculative Decoding via Knowledge Distillation—0
Retrieve Anything To Augment Large Language Models—0
Distilling Efficient Vision Transformers from CNNs for Semantic Segmentation—0
Distillation Improves Visual Place Recognition for Low Quality ImagesCode0
Leveraging Diffusion-Based Image Variations for Robust Training on Poisoned DataCode0
Knowledge Distillation for Anomaly Detection—0
What do larger image classifiers memorise?—0
Applying Knowledge Distillation to Improve Weed Mapping With DronesCode0
Fair Feature Importance Scores for Interpreting Tree-Based Methods and Surrogates—0
DED: Diagnostic Evidence Distillation for acne severity grading on face imagesCode0
Improving Knowledge Distillation with Teacher's Explanation—0
Talking Models: Distill Pre-trained Knowledge to Downstream Models via Interactive Communication—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
Can a student Large Language Model perform as well as it's teacher?—0
Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models—0
KGEx: Explaining Knowledge Graph Embeddings via Subgraph Sampling and Knowledge Distillation—0
Learnable Cross-modal Knowledge Distillation for Multi-modal Learning with Missing Modality—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
Distilling Inductive Bias: Knowledge Distillation Beyond Model Compression—0
Promoting Generalized Cross-lingual Question Answering in Few-resource Scenarios via Self-knowledge DistillationCode0
Show:102550
← PrevPage 46 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