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 1101–1150 of 4240 papers

TitleStatusHype
BJTU-WeChat's Systems for the WMT22 Chat Translation Task—0
AMLN: Adversarial-based Mutual Learning Network for Online Knowledge Distillation—0
Emo Pillars: Knowledge Distillation to Support Fine-Grained Context-Aware and Context-Less Emotion Classification—0
Embedding Compression for Teacher-to-Student Knowledge Transfer—0
Deep Collective Knowledge Distillation—0
A metric learning approach for endoscopic kidney stone identification—0
A Closer Look at Rehearsal-Free Continual Learning—0
AdvFunMatch: When Consistent Teaching Meets Adversarial Robustness—0
A method for estimating forest carbon storage distribution density via artificial intelligence generated content model—0
Adaptive Multiplane Image Generation from a Single Internet Picture—0
Embedded Knowledge Distillation in Depth-Level Dynamic Neural Network—0
EmbedDistill: A Geometric Knowledge Distillation for Information Retrieval—0
Knowledge distillation for optimization of quantized deep neural networks—0
Decoupling Dark Knowledge via Block-wise Logit Distillation for Feature-level Alignment—0
Decouple Non-parametric Knowledge Distillation For End-to-end Speech Translation—0
Decoupled Transformer for Scalable Inference in Open-domain Question Answering—0
Decoupled Transformer for Scalable Inference in Open-domain Question Answering—0
Biologically inspired structure learning with reverse knowledge distillation for spiking neural networks—0
AMD: Automatic Multi-step Distillation of Large-scale Vision Models—0
BiM-VFI: Bidirectional Motion Field-Guided Frame Interpolation for Video with Non-uniform Motions—0
AMD: Adaptive Masked Distillation for Object Detection—0
A Closer Look at Knowledge Distillation with Features, Logits, and Gradients—0
Decoupled Alignment for Robust Plug-and-Play Adaptation—0
De-confounded Data-free Knowledge Distillation for Handling Distribution Shifts—0
Bilateral Memory Consolidation for Continual Learning—0
Always Strengthen Your Strengths: A Drift-Aware Incremental Learning Framework for CTR Prediction—0
Sentence-wise Speech Summarization: Task, Datasets, and End-to-End Modeling with LM Knowledge Distillation—0
Decision Boundary-aware Knowledge Consolidation Generates Better Instance-Incremental Learner—0
Debias the Black-box: A Fair Ranking Framework via Knowledge Distillation—0
Decentralized and Model-Free Federated Learning: Consensus-Based Distillation in Function Space—0
Adaptively Integrated Knowledge Distillation and Prediction Uncertainty for Continual Learning—0
ELAICHI: Enhancing Low-resource TTS by Addressing Infrequent and Low-frequency Character Bigrams—0
ELiTe: Efficient Image-to-LiDAR Knowledge Transfer for Semantic Segmentation—0
Empirical Evaluation of Knowledge Distillation from Transformers to Subquadratic Language Models—0
Enhancing Once-For-All: A Study on Parallel Blocks, Skip Connections and Early Exits—0
Debiased Distillation by Transplanting the Last Layer—0
Debate, Reflect, and Distill: Multi-Agent Feedback with Tree-Structured Preference Optimization for Efficient Language Model Enhancement—0
DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers—0
Dealing with training and test segmentation mismatch: FBK@IWSLT2021—0
Bi-CryptoNets: Leveraging Different-Level Privacy for Encrypted Inference—0
Dealing with Missing Modalities in the Visual Question Answer-Difference Prediction Task through Knowledge Distillation—0
ALP-KD: Attention-Based Layer Projection for Knowledge Distillation—0
Adaptive Label Smoothing with Self-Knowledge in Natural Language Generation—0
DDK: Distilling Domain Knowledge for Efficient Large Language Models—0
DCSNet: A Lightweight Knowledge Distillation-Based Model with Explainable AI for Lung Cancer Diagnosis from Histopathological Images—0
Be Your Own Best Competitor! Multi-Branched Adversarial Knowledge Transfer—0
ESGN: Efficient Stereo Geometry Network for Fast 3D Object Detection—0
DC-CCL: Device-Cloud Collaborative Controlled Learning for Large Vision Models—0
Beyond the Tip of Efficiency: Uncovering the Submerged Threats of Jailbreak Attacks in Small Language Models—0
Efficient Video Segmentation Models with Per-frame Inference—0
Show:102550
← PrevPage 23 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