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 301–350 of 4240 papers

TitleStatusHype
Distillation from Heterogeneous Models for Top-K RecommendationCode1
Distilled Semantics for Comprehensive Scene Understanding from VideosCode1
DistilCSE: Effective Knowledge Distillation For Contrastive Sentence EmbeddingsCode1
Discriminator-Cooperated Feature Map Distillation for GAN CompressionCode1
Boosting Light-Weight Depth Estimation Via Knowledge DistillationCode1
Block-Wisely Supervised Neural Architecture Search With Knowledge DistillationCode1
Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation ModelsCode1
Disentangle and Remerge: Interventional Knowledge Distillation for Few-Shot Object Detection from A Conditional Causal PerspectiveCode1
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language GuidanceCode1
Blockwisely Supervised Neural Architecture Search with Knowledge DistillationCode1
SKDF: A Simple Knowledge Distillation Framework for Distilling Open-Vocabulary Knowledge to Open-world Object DetectorCode1
Distilling Knowledge from Graph Convolutional NetworksCode1
A semi-supervised Teacher-Student framework for surgical tool detection and localizationCode1
Distillation-Based Training for Multi-Exit ArchitecturesCode1
BPKD: Boundary Privileged Knowledge Distillation For Semantic SegmentationCode1
Breaking Modality Gap in RGBT Tracking: Coupled Knowledge DistillationCode1
Black-box Few-shot Knowledge DistillationCode1
Bridge Past and Future: Overcoming Information Asymmetry in Incremental Object DetectionCode1
Adversarially Robust DistillationCode1
Fcaformer: Forward Cross Attention in Hybrid Vision TransformerCode1
CaMEL: Mean Teacher Learning for Image CaptioningCode1
CaKDP: Category-aware Knowledge Distillation and Pruning Framework for Lightweight 3D Object DetectionCode1
Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation?Code1
BKDSNN: Enhancing the Performance of Learning-based Spiking Neural Networks Training with Blurred Knowledge DistillationCode1
A Fast Knowledge Distillation Framework for Visual RecognitionCode1
Action knowledge for video captioning with graph neural networksCode1
Black-Box Attacks on Sequential Recommenders via Data-Free Model ExtractionCode1
Prototype-based Incremental Few-Shot Semantic SegmentationCode1
Boosting Multi-Label Image Classification with Complementary Parallel Self-DistillationCode1
Distilling DETR with Visual-Linguistic Knowledge for Open-Vocabulary Object DetectionCode1
Categorical Relation-Preserving Contrastive Knowledge Distillation for Medical Image ClassificationCode1
CCL: Continual Contrastive Learning for LiDAR Place RecognitionCode1
CEN-HDR: Computationally Efficient neural Network for real-time High Dynamic Range imagingCode1
CEKD: Cross-Modal Edge-Privileged Knowledge Distillation for Semantic Scene Understanding Using Only Thermal ImagesCode1
A framework for benchmarking class-out-of-distribution detection and its application to ImageNetCode1
A Symmetric Dual Encoding Dense Retrieval Framework for Knowledge-Intensive Visual Question AnsweringCode1
CheXseg: Combining Expert Annotations with DNN-generated Saliency Maps for X-ray SegmentationCode1
CLIP-guided Federated Learning on Heterogeneous and Long-Tailed DataCode1
Circumventing Outliers of AutoAugment with Knowledge DistillationCode1
Chinese grammatical error correction based on knowledge distillationCode1
Class Attention Transfer Based Knowledge DistillationCode1
Distilling Large Vision-Language Model with Out-of-Distribution GeneralizabilityCode1
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighterCode1
Class-Incremental Learning by Knowledge Distillation with Adaptive Feature ConsolidationCode1
ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via α-β-DivergenceCode1
Distilling Object Detectors with Feature RichnessCode1
A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank CloneCode1
Class-incremental Novel Class DiscoveryCode1
Class-relation Knowledge Distillation for Novel Class DiscoveryCode1
Distilled Split Deep Neural Networks for Edge-Assisted Real-Time SystemsCode1
Show:102550
← PrevPage 7 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