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/ansfl/learning-based-mems-gyrocompassing
https://github.com/anshu123priya/Real-v-s-Fake-Emotion-Challenge
MicroExpNet: An Extremely Small and Fast Model For Expression Recognition From Face Images
https://github.com/anshu123priya/Real-vs-Fake-Emotion-Challenge
MicroExpNet: An Extremely Small and Fast Model For Expression Recognition From Face Images
https://github.com/antoinebellemare/dat_gpt
https://github.com/antoinedemathelin/openood
OpenOOD: Benchmarking Generalized Out-of-Distribution Detection
https://github.com/apple/ml-mobileclip
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/aquvitae/aquvitae
https://github.com/aradhanacha/aif360
https://github.com/arcee-ai/distillkit
Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs
https://github.com/archettialberto/federated_survival_forests
Heterogeneous Datasets for Federated Survival Analysis Simulation
https://github.com/arcprize/arc-agi-2
https://github.com/armaank/archlectures
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/arodio/ca-fed
Federated Learning Under Intermittent Client Availability and Time-Varying Communication Constraints
https://github.com/aronfothi/mask_cluster_rcnn
https://github.com/arsalan993/Multivariate-timeseries-forecasting-using-TS-decompostion-and-deep-learnring
https://github.com/arsalan993/Univariate-Time-Series-Forecasting-using-decomposition-and-Deep-Learning
https://github.com/artefactory/choice-learn
https://github.com/artemmavrin/focal-loss
https://github.com/artxtech/darknet-rnn
https://github.com/artynet/darknet-alexeyAB
https://github.com/artyompal/kaggle-abstract-reasoning
https://github.com/arunppsg/TadGAN
TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks
https://github.com/aryanasadianuoit/distillation_deep
https://github.com/as-ideas/TransformerTTS
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
https://github.com/askaydevs/distillbert-qa
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
https://github.com/aslialp/HATCNN
Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch
https://github.com/assassint2017/MICCAI-LITS2017
https://github.com/assulthoni/TweetSentimentIndoBERT
IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding
https://github.com/asterisci/point-gcc
https://github.com/atreyasha/mimic3_benchmarks_occlusion
Multitask learning and benchmarking with clinical time series data
https://github.com/atreyasha/mv-temporal-rgan
Multitask learning and benchmarking with clinical time series data
https://github.com/autogluon/tabrepo
TabArena: A Living Benchmark for Machine Learning on Tabular Data
https://github.com/automl/auto-sklearn
https://github.com/automl/nes
Benchmarking Neural Network Robustness to Common Corruptions and Perturbations
https://github.com/avasalya/singleshot6Dpose
Squeezed Deep 6DoF Object Detection Using Knowledge Distillation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.