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 201–250 of 4240 papers

TitleStatusHype
Black-Box Attacks on Sequential Recommenders via Data-Free Model ExtractionCode1
Black-box Few-shot Knowledge DistillationCode1
AIM 2024 Challenge on UHD Blind Photo Quality AssessmentCode1
Adjoined Networks: A Training Paradigm with Applications to Network CompressionCode1
Block-Wisely Supervised Neural Architecture Search With Knowledge DistillationCode1
Aligned Structured Sparsity Learning for Efficient Image Super-ResolutionCode1
Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation?Code1
Boosting Multi-Label Image Classification with Complementary Parallel Self-DistillationCode1
Bootstrapping meaning through listening: Unsupervised learning of spoken sentence embeddingsCode1
DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation TrainerCode1
Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language ModelCode1
Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Large Model EnhancementCode1
Breaking Modality Gap in RGBT Tracking: Coupled Knowledge DistillationCode1
Bridge Past and Future: Overcoming Information Asymmetry in Incremental Object DetectionCode1
DARTS: Double Attention Reference-based Transformer for Super-resolutionCode1
Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation ModelsCode1
C2KD: Cross-Lingual Cross-Modal Knowledge Distillation for Multilingual Text-Video RetrievalCode1
Fcaformer: Forward Cross Attention in Hybrid Vision TransformerCode1
AlphaFold Distillation for Protein DesignCode1
DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech TranslationCode1
CaMEL: Mean Teacher Learning for Image CaptioningCode1
AltDiffusion: A Multilingual Text-to-Image Diffusion ModelCode1
Better Estimation of the KL Divergence Between Language ModelsCode1
CEN-HDR: Computationally Efficient neural Network for real-time High Dynamic Range imagingCode1
DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue GenerationCode1
Dice Semimetric Losses: Optimizing the Dice Score with Soft LabelsCode1
CCL: Continual Contrastive Learning for LiDAR Place RecognitionCode1
Categorical Relation-Preserving Contrastive Knowledge Distillation for Medical Image ClassificationCode1
AMFD: Distillation via Adaptive Multimodal Fusion for Multispectral Pedestrian DetectionCode1
Adaptive Multi-Teacher Knowledge Distillation with Meta-LearningCode1
Adaptive Multi-Teacher Multi-level Knowledge DistillationCode1
Channel Distillation: Channel-Wise Attention for Knowledge DistillationCode1
Understanding the Role of the Projector in Knowledge DistillationCode1
Channel-Aware Distillation Transformer for Depth Estimation on Nano DronesCode1
Channel Gating Neural NetworksCode1
Channel-wise Knowledge Distillation for Dense PredictionCode1
CheXseg: Combining Expert Annotations with DNN-generated Saliency Maps for X-ray SegmentationCode1
Directed Acyclic Transformer for Non-Autoregressive Machine TranslationCode1
BERT-of-Theseus: Compressing BERT by Progressive Module ReplacingCode1
Class Attention Transfer Based Knowledge DistillationCode1
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighterCode1
Class-Balanced Distillation for Long-Tailed Visual RecognitionCode1
Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual LearningCode1
Class-Incremental Learning by Knowledge Distillation with Adaptive Feature ConsolidationCode1
Curriculum Temperature for Knowledge DistillationCode1
Distillation-Based Training for Multi-Exit ArchitecturesCode1
CLIP-guided Federated Learning on Heterogeneous and Long-Tailed DataCode1
CLIP-Embed-KD: Computationally Efficient Knowledge Distillation Using Embeddings as TeachersCode1
CLIP-KD: An Empirical Study of CLIP Model DistillationCode1
AICSD: Adaptive Inter-Class Similarity Distillation for Semantic SegmentationCode1
Show:102550
← PrevPage 5 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