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/KarhouTam/FL-bench
FedMD: Heterogenous Federated Learning via Model Distillation
https://github.com/Karthik-Bhaskar/Context-Based-Question-Answering
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
https://github.com/Kaushalya/medclip
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/KellyYutongHe/Knowledge-Distillation-Net-with-Swish
https://github.com/KevinMIN95/StyleSpeech
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
https://github.com/KingBoyBIT/yolov3test
https://github.com/Koukyosyumei/AIJack
FedMD: Heterogenous Federated Learning via Model Distillation
https://github.com/KrissHs/KIT19
https://github.com/L1aoXingyu/reid_baseline
Semi-Supervised Domain Generalizable Person Re-Identification
https://github.com/LEOCUIZHIHAO/kpmask
https://github.com/LIU1514/Yolov3-
https://github.com/LMJJJJJJ/feature-complexity
Interpreting and Disentangling Feature Components of Various Complexity from DNNs
https://github.com/LTH14/FSKD
Few Sample Knowledge Distillation for Efficient Network Compression
https://github.com/Lackel/DNA
Benchmarking Natural Language Understanding Services for building Conversational Agents
https://github.com/Lamperougeyxy/GHQ
https://github.com/Lan1991Xu/ONE_NeurIPS2018
https://github.com/LazarusNLP/NusaBERT
IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding
https://github.com/LeDuySon/torchreid_uet_lab
Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch
https://github.com/LeHoaiLinh278/mmdetection_dev
https://github.com/LebronGG/PointCnn
https://github.com/Lechatelia/CRCD
https://github.com/Lechatelia/detection
https://github.com/LeoXuZH/CervicalCancerDetection
https://github.com/Linxuxin/mmdetection-mine
https://github.com/LiuShenLan/mmdetection
https://github.com/Lmath11/darknet
https://github.com/LokeZhou/mydetection
https://github.com/MIC-DKFZ/DetectionAndRegression
https://github.com/MIC-DKFZ/RegRCNN
https://github.com/MIC-DKFZ/nnDetection
Evaluating Large-Vocabulary Object Detectors: The Devil is in the Details
https://github.com/MKLab-ITI/FIVR-200K
https://github.com/MKYucel/zero_shot_corruption_benchmarks
Benchmarking Neural Network Robustness to Common Corruptions and Perturbations
https://github.com/MLforHealth/rl_representations
https://github.com/MOHAMEDELDAKDOUKY/bert_adjusted
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/MR-HosseinzadehTaher/BenchmarkTransferLearning
A Systematic Benchmarking Analysis of Transfer Learning for Medical Image Analysis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.