https://github.com/roymiles/simple-recipe-distillation
공식 코드Understanding the Role of the Projector in Knowledge Distillation
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/roymiles/vkd
공식 코드$V_kD:$ Improving Knowledge Distillation using Orthogonal Projections
https://github.com/royson/reefl
공식 코드Recurrent Early Exits for Federated Learning with Heterogeneous Clients
https://github.com/rr-learning/trifinger-rl-example
공식 코드Benchmarking Offline Reinforcement Learning on Real-Robot Hardware
https://github.com/rr-learning/trifinger_rl_datasets
공식 코드Benchmarking Offline Reinforcement Learning on Real-Robot Hardware
https://github.com/rramosp/llpeo
공식 코드On-orbit model training for satellite imagery with label proportions
https://github.com/rsantana-isg/morl_benchmark
공식 코드Benchmarking MOEAs for solving continuous multi-objective RL problems
https://github.com/rst-tu-dortmund/lerojd
공식 코드https://github.com/rtu715/nas-bench-360
공식 코드NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Tasks
https://github.com/ruathudo/tfw2v
공식 코드TFW2V: An Enhanced Document Similarity Method for the Morphologically Rich Finnish Language
https://github.com/rubenrtorrado/GVGAI_GYM
공식 코드https://github.com/rucaibox/ckd-mdsr
공식 코드https://github.com/rucaibox/dagfm
공식 코드Directed Acyclic Graph Factorization Machines for CTR Prediction via Knowledge Distillation
https://github.com/rucaibox/jiuzhang3.0
공식 코드JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
https://github.com/rucaibox/recbole2.0
공식 코드RecBole 2.0: Towards a More Up-to-Date Recommendation Library
https://github.com/rucaibox/ufin
공식 코드UFIN: Universal Feature Interaction Network for Multi-Domain Click-Through Rate Prediction
https://github.com/rufaim/routing-by-memory
공식 코드https://github.com/ruipingl/skr_pea
공식 코드TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation
https://github.com/ruipingl/transkd
공식 코드TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation
https://github.com/runpeidong/act
공식 코드https://github.com/runpeidong/pointdistiller
공식 코드PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection
https://github.com/russelljeffrey/FedBrain-Distill
공식 코드https://github.com/rvandewater/recipys
공식 코드Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML
https://github.com/rvandewater/yaib
공식 코드Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML
https://github.com/rvandewater/yaib-cohorts
공식 코드Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML
https://github.com/rvandewater/yaib-models
공식 코드Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML
https://github.com/rvivek3/anchorpoints
공식 코드https://github.com/rvl-lab-utoronto/bfp
공식 코드Preserving Linear Separability in Continual Learning by Backward Feature Projection
https://github.com/rvp-group/vbr-devkit
공식 코드https://github.com/rwgai/rwds
공식 코드Benchmarking Object Detectors under Real-World Distribution Shifts in Satellite Imagery
https://github.com/ryanliu30/kd4jets
공식 코드Efficient and Robust Jet Tagging at the LHC with Knowledge Distillation
https://github.com/rycolab/kl-rb
공식 코드Better Estimation of the KL Divergence Between Language Models
https://github.com/ryienh/gnn-ops-benchmark
공식 코드Operation-Level Performance Benchmarking of Graph Neural Networks for Scientific Applications
https://github.com/ryliu68/igmu
공식 코드https://github.com/ryojitanabe/as_bbo
공식 코드Benchmarking Feature-based Algorithm Selection Systems for Black-box Numerical Optimization
https://github.com/ryojitanabe/de_bbobmixint
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.