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

Showing 301350 of 4240 papers

TitleStatusHype
PEA-Diffusion: Parameter-Efficient Adapter with Knowledge Distillation in non-English Text-to-Image GenerationCode1
Some Like It Small: Czech Semantic Embedding Models for Industry ApplicationsCode1
HoVer-UNet: Accelerating HoVerNet with UNet-based multi-class nuclei segmentation via knowledge distillationCode1
Point, Segment and Count: A Generalized Framework for Object CountingCode1
FreeKD: Knowledge Distillation via Semantic Frequency PromptCode1
Expanding Scene Graph Boundaries: Fully Open-vocabulary Scene Graph Generation via Visual-Concept Alignment and RetentionCode1
Quantized Distillation: Optimizing Driver Activity Recognition Models for Resource-Constrained EnvironmentsCode1
Cross-Level Distillation and Feature Denoising for Cross-Domain Few-Shot ClassificationCode1
Implicit Chain of Thought Reasoning via Knowledge DistillationCode1
Multilingual DistilWhisper: Efficient Distillation of Multi-task Speech Models via Language-Specific ExpertsCode1
Distilling Out-of-Distribution Robustness from Vision-Language Foundation ModelsCode1
One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge DistillationCode1
Label Poisoning is All You NeedCode1
Understanding the Effects of Projectors in Knowledge DistillationCode1
MonoSKD: General Distillation Framework for Monocular 3D Object Detection via Spearman Correlation CoefficientCode1
Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational AgentsCode1
Transport-Hub-Aware Spatial-Temporal Adaptive Graph Transformer for Traffic Flow PredictionCode1
Online Speculative DecodingCode1
DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech TranslationCode1
A Discrepancy Aware Framework for Robust Anomaly DetectionCode1
LumiNet: The Bright Side of Perceptual Knowledge DistillationCode1
SEA: Sparse Linear Attention with Estimated Attention MaskCode1
NAYER: Noisy Layer Data Generation for Efficient and Effective Data-free Knowledge DistillationCode1
DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge DistillationCode1
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language GuidanceCode1
Weight Averaging Improves Knowledge Distillation under Domain ShiftCode1
DFIL: Deepfake Incremental Learning by Exploiting Domain-invariant Forgery CluesCode1
FDCNet: Feature Drift Compensation Network for Class-Incremental Weakly Supervised Object LocalizationCode1
Rethinking Momentum Knowledge Distillation in Online Continual LearningCode1
COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using TransformersCode1
SpikeBERT: A Language Spikformer Learned from BERT with Knowledge DistillationCode1
Bridging Cross-task Protocol Inconsistency for Distillation in Dense Object DetectionCode1
DM-VTON: Distilled Mobile Real-time Virtual Try-OnCode1
Sentence Embedding Models for Ancient Greek Using Multilingual Knowledge DistillationCode1
Ground-to-Aerial Person Search: Benchmark Dataset and ApproachCode1
FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated LearningCode1
SpikingBERT: Distilling BERT to Train Spiking Language Models Using Implicit DifferentiationCode1
FedDAT: An Approach for Foundation Model Finetuning in Multi-Modal Heterogeneous Federated LearningCode1
AltDiffusion: A Multilingual Text-to-Image Diffusion ModelCode1
Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual LearningCode1
Token-Scaled Logit Distillation for Ternary Weight Generative Language ModelsCode1
Multi-Label Knowledge DistillationCode1
Multi-View Fusion and Distillation for Subgrade Distresses Detection based on 3D-GPRCode1
AICSD: Adaptive Inter-Class Similarity Distillation for Semantic SegmentationCode1
One-stage Low-resolution Text Recognition with High-resolution Knowledge TransferCode1
VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPsCode1
Transferable Graph Structure Learning for Graph-based Traffic Forecasting Across CitiesCode1
Baby Llama: knowledge distillation from an ensemble of teachers trained on a small dataset with no performance penaltyCode1
Beyond Generic: Enhancing Image Captioning with Real-World Knowledge using Vision-Language Pre-Training ModelCode1
NormKD: Normalized Logits for Knowledge DistillationCode1
Show:102550
← PrevPage 7 of 85Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ScaleKD (T:BEiT-L S:ViT-B/14)Top-1 accuracy %86.43Unverified
2ScaleKD (T:Swin-L S:ViT-B/16)Top-1 accuracy %85.53Unverified
3ScaleKD (T:Swin-L S:ViT-S/16)Top-1 accuracy %83.93Unverified
4ScaleKD (T:Swin-L S:Swin-T)Top-1 accuracy %83.8Unverified
5KD++(T: regnety-16GF S:ViT-B)Top-1 accuracy %83.6Unverified
6VkD (T:RegNety 160 S:DeiT-S)Top-1 accuracy %82.9Unverified
7SpectralKD (T:Swin-S S:Swin-T)Top-1 accuracy %82.7Unverified
8ScaleKD (T:Swin-L S:ResNet-50)Top-1 accuracy %82.55Unverified
9DiffKD (T:Swin-L S: Swin-T)Top-1 accuracy %82.5Unverified
10DIST (T: Swin-L S: Swin-T)Top-1 accuracy %82.3Unverified
#ModelMetricClaimedVerifiedStatus
1SRD (T:resnet-32x4, S:shufflenet-v2)Top-1 Accuracy (%)79.86Unverified
2shufflenet-v2(T:resnet-32x4, S:shufflenet-v2)Top-1 Accuracy (%)78.76Unverified
3MV-MR (T: CLIP/ViT-B-16 S: resnet50)Top-1 Accuracy (%)78.6Unverified
4resnet8x4 (T: resnet32x4 S: resnet8x4)Top-1 Accuracy (%)78.28Unverified
5resnet8x4 (T: resnet32x4 S: resnet8x4 [modified])Top-1 Accuracy (%)78.08Unverified
6ReviewKD++(T:resnet-32x4, S:shufflenet-v2)Top-1 Accuracy (%)77.93Unverified
7ReviewKD++(T:resnet-32x4, S:shufflenet-v1)Top-1 Accuracy (%)77.68Unverified
8resnet8x4 (T: resnet32x4 S: resnet8x4)Top-1 Accuracy (%)77.5Unverified
9resnet8x4 (T: resnet32x4 S: resnet8x4)Top-1 Accuracy (%)76.68Unverified
10resnet8x4 (T: resnet32x4 S: resnet8x4)Top-1 Accuracy (%)76.31Unverified
#ModelMetricClaimedVerifiedStatus
1LSHFM (T: ResNet101 S: ResNet50)mAP93.17Unverified
2LSHFM (T: ResNet101 S: MobileNetV2)mAP90.14Unverified
#ModelMetricClaimedVerifiedStatus
1TIE-KD (T: Adabins S: MobileNetV2)RMSE2.43Unverified