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/gmpoli/electramed
https://github.com/goksenin-uav/torchreid-pip
Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch
https://github.com/gokulprasadthekkel/pytorch-multi-class-focal-loss
https://github.com/gonglinyuan/metro_t0
Multitask Prompted Training Enables Zero-Shot Task Generalization
https://github.com/goodluck4s/bert-
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/google-deepmind/optax
Benchopt: Reproducible, efficient and collaborative optimization benchmarks
https://github.com/google-research-datasets/RxR
https://github.com/google-research-datasets/bam
Benchmarking Attribution Methods with Relative Feature Importance
https://github.com/google-research/big_transfer
Knowledge distillation: A good teacher is patient and consistent
https://github.com/google-research/bigbird
https://github.com/google-research/bleurt
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/google-research/tapas
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/gotbutchi/Coderschool-Machine-Learning-Final-Project
https://github.com/gpapamak/distilling_model_knowledge
https://github.com/gqding/SUDF
Hyperspectral Image Dataset for Benchmarking on Salient Object Detection
https://github.com/grip-unina/m3dsynth
M3Dsynth: A dataset of medical 3D images with AI-generated local manipulations
https://github.com/guillaumejaume/tuto-dl-on-graphs
https://github.com/guillempla/Fashion-MNIST-Neural-Network
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
https://github.com/guyd1995/lra-benchmark
https://github.com/guyd1995/lra-benchmarks
https://github.com/gyes00205/waymo_tf_object_detection
https://github.com/gyutaaa/gyutaekim-2016011728
https://github.com/h2oai/h2o-3
https://github.com/hSDB-instrument/hsdb-mmdetection
https://github.com/hackerchenzhuo/LaKo
Distilling Knowledge from Reader to Retriever for Question Answering
https://github.com/hahayonghuming/VDACs
https://github.com/hahnyuan/llmviewer
https://github.com/haithink/myWindowsDarknet
https://github.com/halo090770/bert
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/hamidreza-dastmalchi/3dd-tta
Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions
https://github.com/hamzaMahdi/darknet
https://github.com/hangkongbei/mmdetection
https://github.com/hankpark0706/darknet
https://github.com/hanoonaR/object-centric-ovd
Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
https://github.com/haro-cyber/KnowledgeDistillation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.