Papers with Code 아카이브
Knowledge Distillation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 11
- 보존된 평가 기록
- 90
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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/MIC-DKFZ/nnunet
공식 코드nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentation
https://github.com/MIMUW-RL/Unified-Long-Horizon-Time-Series-Benchmark
공식 코드https://github.com/MIRALab-USTC/GraphAKD
공식 코드Compressing Deep Graph Neural Networks via Adversarial Knowledge Distillation
https://github.com/MLforHealth/CausalDA
공식 코드Pulling Up by the Causal Bootstraps: Causal Data Augmentation for Pre-training Debiasing
https://github.com/MLforHealth/S2SD
공식 코드S2SD: Simultaneous Similarity-based Self-Distillation for Deep Metric Learning
https://github.com/MSiam/TFSegmentation
공식 코드https://github.com/MVIG-SJTU/AlphaPose
공식 코드AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time
https://github.com/Maddy12/UnderstandingVisualTextModels
공식 코드Probing Conceptual Understanding of Large Visual-Language Models
https://github.com/Madjid-CH/auto-mixer
공식 코드MixMAS: A Framework for Sampling-Based Mixer Architecture Search for Multimodal Fusion and Learning
https://github.com/ManifoldRG/MultiNet
공식 코드Benchmarking Vision, Language, & Action Models on Robotic Learning Tasks
https://github.com/MatteoEURECOM/LIDAR-mmWave-Beam-Selection
공식 코드LIDAR and Position-Aided mmWave Beam Selection with Non-local CNNs and Curriculum Training
https://github.com/MediaBrain-SJTU/RD
공식 코드https://github.com/MichiganCOG/ViP
공식 코드https://github.com/Microsoft/Graphormer
공식 코드Benchmarking Graphormer on Large-Scale Molecular Modeling Datasets
https://github.com/MingLunHan/CIF-PyTorch
공식 코드https://github.com/MingiJi/FRSKD
공식 코드Refine Myself by Teaching Myself: Feature Refinement via Self-Knowledge Distillation
https://github.com/MinkaiXu/RSL-NMT
공식 코드Reciprocal Supervised Learning Improves Neural Machine Translation
https://github.com/Mithunjha/EarEEG_KnowledgeDistillation
공식 코드A Knowledge Distillation Framework For Enhancing Ear-EEG Based Sleep Staging With Scalp-EEG Data
https://github.com/MohamedAfham/CD_HPE
공식 코드https://github.com/Mohit-Mithra/Face-Recognition-Systems-with-lip-movement-pattern
공식 코드AuthNet: A Deep Learning based Authentication Mechanism using Temporal Facial Feature Movements
https://github.com/MorenoLaQuatra/ARCH
공식 코드Benchmarking Representations for Speech, Music, and Acoustic Events
https://github.com/Muhammad-Huzaifaa/Defensive_Diffusion
공식 코드On enhancing the robustness of Vision Transformers: Defensive Diffusion
https://github.com/NASA-IMPACT/Prithvi-EO-2.0
공식 코드Prithvi-EO-2.0: A Versatile Multi-Temporal Foundation Model for Earth Observation Applications
https://github.com/NJUNLP/MT-Patcher
공식 코드https://github.com/NREL/OPFLearn.jl
공식 코드OPF-Learn: An Open-Source Framework for Creating Representative AC Optimal Power Flow Datasets
https://github.com/NUST-Machine-Intelligence-Laboratory/weblyFG-dataset
공식 코드Webly Supervised Fine-Grained Recognition: Benchmark Datasets and An Approach
https://github.com/NVIDIA/DeepLearningExamples
공식 코드A Framework for Large Scale Synthetic Graph Dataset Generation
https://github.com/NVIDIA/DeepLearningExamples/tree/master/Tools/PyTorch/TimeSeriesPredictionPlatform
공식 코드TSPP: A Unified Benchmarking Tool for Time-series Forecasting
https://github.com/NVlabs/DICOD
공식 코드https://github.com/NanmanasLin/Application-of-natural-language-processing-for-finding-semantic-relation-of-elusive-natural-resource
공식 코드Geological Inference from Textual Data using Word Embeddings
https://github.com/NathanDoumeche/WeaKL
공식 코드https://github.com/Natlem/M-HTCN
공식 코드Incremental Multi-Target Domain Adaptation for Object Detection with Efficient Domain Transfer
https://github.com/Natural-Language-Processing-Elm/open_universal_arabic_asr_leaderboard
공식 코드https://github.com/NeelKanwal/Vision-Transformers-for-Small-Histological-Datasets-Learned-Through-Knowledge-Distillation
공식 코드Vision Transformers for Small Histological Datasets Learned through Knowledge Distillation
https://github.com/NeosKnight233/FaMSS
공식 코드Selected Languages are All You Need for Cross-lingual Truthfulness Transfer
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.