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/ZTao-z/multiflow-resnet-ssd
https://github.com/ZZR8066/mmdetection-GaofenCompetition
https://github.com/ZackPashkin/text2cartoon-pytorch-CLIP
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/Zernach/Fashion-MNIST
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
https://github.com/ZhaoChuyang/trans-person-search
https://github.com/ZhenJie-Zhang/darknet_shoe
https://github.com/ZhengPeng7/motion_magnification_learning-based
https://github.com/a736875071/clip-vit-large-patch14
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/aabbas90/cluster-fug
https://github.com/aakashjhawar/traffic-sign-detection
https://github.com/abcxs/building_extraction
https://github.com/abcxs/polyrnn
https://github.com/abhiagg92/bert_sentiment
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/aclyde11/RNNGenerator
Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models
https://github.com/acmmmsys/2021-grandchallenge-cheapfakes
COSMOS: Catching Out-of-Context Misinformation with Self-Supervised Learning
https://github.com/adap/flower
https://github.com/adhyasuman/ntms_dropout_analysis
Improving Neural Topic Models with Wasserstein Knowledge Distillation
https://github.com/adlnlp/Midas
MIDAS: Multi-level Intent, Domain, And Slot Knowledge Distillation for Multi-turn NLU
https://github.com/aerialroboticsgroup/agile-tethered-perching
https://github.com/agentification/language-integrated-vi
InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback
https://github.com/agrawalparth10/Face-is-the-Key
https://github.com/agutuyen-dev/darknet
https://github.com/ahhan02/darknet-alex
https://github.com/ai-forever/ru-clip
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/ai-unicamp/tts-objective-metrics
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
https://github.com/aida-ugent/NRLBenchmark
Benchmarking Network Embedding Models for Link Prediction: Are We Making Progress?
https://github.com/aioz-ai/multigraphfl
https://github.com/airglow/simitate
https://github.com/airglow/simitate_imitation_learning_benchmark
https://github.com/aitorlucasc/uhc_distillation
https://github.com/aizhanti/jarunc
https://github.com/ajayjain/vectorascent
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/akarimoon/xtask_mt
https://github.com/akulkailwoo/zalando-fashion-mnist
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
https://github.com/aleflabo/HypAD
TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.