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 2351–2400 of 4240 papers

TitleStatusHype
Towards Comparable Knowledge Distillation in Semantic Image Segmentation—0
Leveraging ASR Pretrained Conformers for Speaker Verification through Transfer Learning and Knowledge Distillation—0
A deep Natural Language Inference predictor without language-specific training data—0
DMKD: Improving Feature-based Knowledge Distillation for Object Detection Via Dual Masking Augmentation—0
Knowledge Distillation Layer that Lets the Student DecideCode0
Probabilistic Self-supervised Learning via Scoring Rules Minimization—0
TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models—0
Fast and High-Performance Learned Image Compression With Improved Checkerboard Context Model, Deformable Residual Module, and Knowledge Distillation—0
A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking—0
On the Query Strategies for Efficient Online Active Distillation—0
Prior Knowledge Guided Network for Video Anomaly Detection—0
Knowledge Distillation from Non-streaming to Streaming ASR Encoder using Auxiliary Non-streaming Layer—0
Towards Long-Tailed Recognition for Graph Classification via Collaborative Experts—0
MoMA: Momentum Contrastive Learning with Multi-head Attention-based Knowledge Distillation for Histopathology Image AnalysisCode0
Adversarial Finetuning with Latent Representation Constraint to Mitigate Accuracy-Robustness Tradeoff—0
Exploring Multi-Modal Contextual Knowledge for Open-Vocabulary Object Detection—0
Distilled GPT for Source Code SummarizationCode0
SynthDistill: Face Recognition with Knowledge Distillation from Synthetic DataCode0
Boosting Residual Networks with Group KnowledgeCode0
Improving Knowledge Distillation for BERT Models: Loss Functions, Mapping Methods, and Weight Tuning—0
REFT: Resource-Efficient Federated Training Framework for Heterogeneous and Resource-Constrained Environments—0
Self-Supervised Representation Learning with Cross-Context Learning between Global and Hypercolumn Features—0
3D Face Alignment Through Fusion of Head Pose Information and Features—0
Fall Detection using Knowledge Distillation Based Long short-term memory for Offline Embedded and Low Power Devices—0
DLIP: Distilling Language-Image Pre-training—0
Efficient Controllable Multi-Task Architectures—0
Multimodal Locally Enhanced Transformer for Continuous Sign Language Recognition—0
Representation Disparity-aware Distillation for 3D Object Detection—0
Unlimited Knowledge Distillation for Action Recognition in the Dark—0
CCFace: Classification Consistency for Low-Resolution Face Recognition—0
Learning Lightweight Object Detectors via Multi-Teacher Progressive Distillation—0
Learning Through Guidance: Knowledge Distillation for Endoscopic Image Classification—0
Radio2Text: Streaming Speech Recognition Using mmWave Radio Signals—0
SkinDistilViT: Lightweight Vision Transformer for Skin Lesion ClassificationCode0
A Survey on Model Compression for Large Language Models—0
Distilling Knowledge from Resource Management Algorithms to Neural Networks: A Unified Training Assistance Approach—0
Complex Facial Expression Recognition Using Deep Knowledge Distillation of Basic FeaturesCode0
Continual Face Forgery Detection via Historical Distribution Preserving—0
Towards General and Fast Video Derain via Knowledge Distillation—0
Sci-CoT: Leveraging Large Language Models for Enhanced Knowledge Distillation in Small Models for Scientific QA—0
FPGA Resource-aware Structured Pruning for Real-Time Neural Networks—0
Enhancing Adversarial Robustness in Low-Label Regime via Adaptively Weighted Regularization and Knowledge DistillationCode0
Teacher-Student Architecture for Knowledge Distillation: A Survey—0
Efficient Temporal Sentence Grounding in Videos with Multi-Teacher Knowledge DistillationCode0
Adapter-based Selective Knowledge Distillation for Federated Multi-domain Meeting Summarization—0
Few-shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge DistillationCode0
Class Incremental Learning with Self-Supervised Pre-Training and Prototype Learning—0
Scene-aware Human Pose Generation using Transformer—0
Eyelid’s Intrinsic Motion-aware Feature Learning for Real-time Eyeblink Detection in the WildCode0
Improved Knowledge Distillation for Crowd Counting on IoT DeviceCode0
Show:102550
← PrevPage 48 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