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 51–100 of 4240 papers

TitleStatusHype
Self-Training with Direct Preference Optimization Improves Chain-of-Thought ReasoningCode2
ESP-MedSAM: Efficient Self-Prompting SAM for Universal Domain-Generalized Medical Image SegmentationCode2
Progressive Pretext Task Learning for Human Trajectory PredictionCode2
Accessing Vision Foundation Models at ImageNet-level CostsCode2
Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language ModelsCode2
A Unified Framework for 3D Scene UnderstandingCode2
Improving Zero-shot Generalization of Learned Prompts via Unsupervised Knowledge DistillationCode2
Dual-Space Knowledge Distillation for Large Language ModelsCode2
Can LLMs Learn by Teaching for Better Reasoning? A Preliminary StudyCode2
From Instance Training to Instruction Learning: Task Adapters Generation from InstructionsCode2
Improving the Training of Rectified FlowsCode2
Rethinking Transformer-Based Blind-Spot Network for Self-Supervised Image DenoisingCode2
Optimization Methods for Personalizing Large Language Models through Retrieval AugmentationCode2
Diffusion Time-step Curriculum for One Image to 3D GenerationCode2
Pre-trained Vision and Language Transformers Are Few-Shot Incremental LearnersCode2
ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt TuningCode2
Scale Decoupled DistillationCode2
Knowledge Distillation in YOLOX-ViT for Side-Scan Sonar Object DetectionCode2
CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-TuningCode2
V_kD: Improving Knowledge Distillation using Orthogonal ProjectionsCode2
On the Road to Portability: Compressing End-to-End Motion Planner for Autonomous DrivingCode2
A Cognitive-Based Trajectory Prediction Approach for Autonomous DrivingCode2
Sinkhorn Distance Minimization for Knowledge DistillationCode2
PromptMM: Multi-Modal Knowledge Distillation for Recommendation with Prompt-TuningCode2
Incremental Sequence Labeling: A Tale of Two ShiftsCode2
LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval and DistillationCode2
Large Language Models are Efficient Learners of Noise-Robust Speech RecognitionCode2
OBSeg: Accurate and Fast Instance Segmentation Framework Using Segmentation Foundation Models with Oriented Bounding Box PromptsCode2
Progressive Knowledge Distillation Of Stable Diffusion XL Using Layer Level LossCode2
LiSA: LiDAR Localization with Semantic AwarenessCode2
VkD: Improving Knowledge Distillation using Orthogonal ProjectionsCode2
Scaled Decoupled DistillationCode2
Point Segment and Count: A Generalized Framework for Object CountingCode2
TinySAM: Pushing the Envelope for Efficient Segment Anything ModelCode2
Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model InferenceCode2
LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPSCode2
Low-latency Real-time Voice Conversion on CPUCode2
Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio ModelsCode2
Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel BaselineCode2
EPTQ: Enhanced Post-Training Quantization via Hessian-guided Network-wise OptimizationCode2
LibreFace: An Open-Source Toolkit for Deep Facial Expression AnalysisCode2
ConDistFL: Conditional Distillation for Federated Learning from Partially Annotated DataCode2
A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and FutureCode2
DOT: A Distillation-Oriented TrainerCode2
MiniLLM: Knowledge Distillation of Large Language ModelsCode2
Are Large Kernels Better Teachers than Transformers for ConvNets?Code2
CoLaDa: A Collaborative Label Denoising Framework for Cross-lingual Named Entity RecognitionCode2
Lion: Adversarial Distillation of Proprietary Large Language ModelsCode2
OccDepth: A Depth-Aware Method for 3D Semantic Scene CompletionCode2
Social4Rec: Distilling User Preference from Social Graph for Video Recommendation in TencentCode2
Show:102550
← PrevPage 2 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