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/DataXujing/Cascade_RCNN_mmdetection
https://github.com/DaveFClarke/ml_bias_checking
https://github.com/DaveKim3872/nasbench-hpc
NAS-Bench-101: Towards Reproducible Neural Architecture Search
https://github.com/Davidnet/TFSegmentation
https://github.com/DecentMakeover/detection
https://github.com/DecentMakeover/mdetect
https://github.com/Deci-AI/super-gradients
https://github.com/DeepMicroscopy/nnUNet
nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentation
https://github.com/DefangChen/OKDDip
https://github.com/DeligientSloth/QQsim
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/DeligientSloth/bert-tensorflow
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/Denys88/rl_games
https://github.com/DetectionTeamUCAS/RetinaNet_Tensorflow_Rotation
https://github.com/DevPranjal/reproduction-review-kd
https://github.com/DevSinghSachan/art
Multitask Prompted Training Enables Zero-Shot Task Generalization
https://github.com/Devwalkar/BOC-KD
Online Ensemble Model Compression using Knowledge Distillation
https://github.com/DhruvMakwana/Global-Wheat-Detection
https://github.com/Diegomangasco/Vision-Language-AML
Domain2Vec: Domain Embedding for Unsupervised Domain Adaptation
https://github.com/DonCorle0ne/damage_detection
https://github.com/Dongdongshe/mlfuzz
https://github.com/Dongximing/Mimic3
Multitask learning and benchmarking with clinical time series data
https://github.com/DoubleBlindGithub/M3
Multitask learning and benchmarking with clinical time series data
https://github.com/DrMMZ/RetinaNet
https://github.com/DunZhang/KnowledgeDistillation
https://github.com/EMsnap/RobotSorting
https://github.com/ENSTA-U2IS-AI/torch-uncertainty
https://github.com/EPFL-VILAB/XDEnsembles
Benchmarking Neural Network Robustness to Common Corruptions and Perturbations
https://github.com/ESBigeard/paper_graph
BioSentVec: creating sentence embeddings for biomedical texts
https://github.com/Ecgbert/Grad_CAM_PLUS_PLUS
Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
https://github.com/Edge-AI-Acceleration-Lab/RBFleX-NAS
NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size
https://github.com/EkdeepSLubana/OrthoReg
Faster gaze prediction with dense networks and Fisher pruning
https://github.com/ElenaRyumina/EMO-AffectNetModel
https://github.com/ElliotY-ML/Hippocampus_Segmentation_MRI
https://github.com/EmreTaha/shortcut-perspective-TF2
https://github.com/EpistasisLab/tpot
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.