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 3451–3500 of 4240 papers

TitleStatusHype
Mixed Sample Augmentation for Online Distillation—0
Online Distilling from Checkpoints for Neural Machine Translation—0
Online Hyperparameter Meta-Learning with Hypergradient Distillation—0
Online Knowledge Distillation via Multi-branch Diversity Enhancement—0
Online Knowledge Distillation with Reward Guidance—0
Online Policy Distillation with Decision-Attention—0
Online pre-training with long-form videos—0
Online Sensor Hallucination via Knowledge Distillation for Multimodal Image Classification—0
On Multilingual Encoder Language Model Compression for Low-Resource Languages—0
On Neural Network Equivalence Checking using SMT Solvers—0
On Reducing Activity with Distillation and Regularization for Energy Efficient Spiking Neural Networks—0
On Self-Distilling Graph Neural Network—0
On student-teacher deviations in distillation: does it pay to disobey?—0
On the benefits of knowledge distillation for adversarial robustness—0
On the Compression of Language Models for Code: An Empirical Study on CodeBERT—0
On the Demystification of Knowledge Distillation: A Residual Network Perspective—0
On The Distribution of Penultimate Activations of Classification Networks—0
On the Efficacy of Knowledge Distillation—0
On the Efficiency of Subclass Knowledge Distillation in Classification Tasks—0
On the Impact of Knowledge Distillation for Model Interpretability—0
On the Impact of White-box Deployment Strategies for Edge AI on Latency and Model Performance—0
On the Interplay Between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis—0
On the Orthogonality of Knowledge Distillation with Other Techniques: From an Ensemble Perspective—0
On the Query Strategies for Efficient Online Active Distillation—0
Analysis of Knowledge Transfer in Kernel Regime—0
Open-Set Fine-Grained Retrieval via Prompting Vision-Language Evaluator—0
Open-set Short Utterance Forensic Speaker Verification using Teacher-Student Network with Explicit Inductive Bias—0
Open Vocabulary 3D Scene Understanding via Geometry Guided Self-Distillation—0
Open-Vocabulary Object Detection using Pseudo Caption Labels—0
Open-Vocabulary Object Detection with Meta Prompt Representation and Instance Contrastive Optimization—0
Open World DETR: Transformer based Open World Object Detection—0
Leveraging Complementary Attention maps in vision transformers for OCT image analysis—0
OplixNet: Towards Area-Efficient Optical Split-Complex Networks with Real-to-Complex Data Assignment and Knowledge Distillation—0
Optical Flow Distillation: Towards Efficient and Stable Video Style Transfer—0
Optimising TinyML with Quantization and Distillation of Transformer and Mamba Models for Indoor Localisation on Edge Devices—0
Optimizing Knowledge Distillation in Transformers: Enabling Multi-Head Attention without Alignment Barriers—0
Optimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques—0
Optimizing Multi-Gateway LoRaWAN via Cloud-Edge Collaboration and Knowledge Distillation—0
Optimizing speed/accuracy trade-off for person re-identification via knowledge distillation—0
Learning Deep and Compact Models for Gesture RecognitionCode0
Improved Knowledge Distillation via Full Kernel Matrix TransferCode0
Learning Efficient Detector with Semi-supervised Adaptive DistillationCode0
Efficient Logit-based Knowledge Distillation of Deep Spiking Neural Networks for Full-Range Timestep DeploymentCode0
TernaryBERT: Distillation-aware Ultra-low Bit BERTCode0
Training on the Test Model: Contamination in Ranking DistillationCode0
Leaning Compact and Representative Features for Cross-Modality Person Re-IdentificationCode0
Beyond the Limitation of Monocular 3D Detector via Knowledge DistillationCode0
ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake ImagesCode0
Beyond Conventional Transformers: The Medical X-ray Attention (MXA) Block for Improved Multi-Label Diagnosis Using Knowledge DistillationCode0
Pretrained Speech Encoders and Efficient Fine-tuning Methods for Speech Translation: UPC at IWSLT 2022Code0
Show:102550
← PrevPage 70 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