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/detecting-cheapfakes/detecting-cheapfakes-code
COSMOS: Catching Out-of-Context Misinformation with Self-Supervised Learning
https://github.com/detectionteamucas/retinanet_tensorflow
https://github.com/dfcf93/MSMARCO
MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
https://github.com/dhansmair/flamingo-mini
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/dhifoster/msc-birkbeck-ml-cwk
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
https://github.com/dimahwang88/mmdetection-multigpu-train
https://github.com/diogenes0319/FedMD_clean
FedMD: Heterogenous Federated Learning via Model Distillation
https://github.com/dishen12/py03
https://github.com/divyakraman/Domain-Adaptive-Knowledge-Distillation-for-Driving-Scene-Semantic-Segmentation
Domain Adaptive Knowledge Distillation for Driving Scene Semantic Segmentation
https://github.com/dizhongzhu/Humanbody_Literatures
PoseNet3D: Learning Temporally Consistent 3D Human Pose via Knowledge Distillation
https://github.com/dmachlanski/benchpress-dm
Benchpress: A Scalable and Versatile Workflow for Benchmarking Structure Learning Algorithms
https://github.com/dmitrykazhdan/MEME-RNN-XAI
Multitask learning and benchmarking with clinical time series data
https://github.com/dngback/co-forget-protocol
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
https://github.com/dogyoonlee/RSMix
Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions
https://github.com/dogyoonlee/RSMix-official
Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions
https://github.com/donghang941114/mmdetection_my
https://github.com/dortsur/heavywater_simplexwater
WaterBench: Towards Holistic Evaluation of Watermarks for Large Language Models
https://github.com/dr-aheydari/SoftAdapt
Going Beyond Classification Accuracy Metrics in Model Compression
https://github.com/ds-academy/TadGAN
TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks
https://github.com/dsindex/iclassifier
On the Effect of Dropping Layers of Pre-trained Transformer Models
https://github.com/dtabas/epymarl
https://github.com/dthiagarajan/ptb-xl-research
Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL
https://github.com/dti-research/SenseAct
Benchmarking Reinforcement Learning Algorithms on Real-World Robots
https://github.com/dtthi/darknetAlexeyAB
https://github.com/ducha-aiki/pydegensac
Image Matching across Wide Baselines: From Paper to Practice
https://github.com/ducha-aiki/pymagsac
Image Matching across Wide Baselines: From Paper to Practice
https://github.com/dunni3/keypoint-diffusion
Benchmarking Generated Poses: How Rational is Structure-based Drug Design with Generative Models?
https://github.com/dvlab-research/LBGAT
https://github.com/dvlab-research/reviewkd
https://github.com/dwaithe/darknet3AB
https://github.com/dyabel/detpro
Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
https://github.com/dyjdongyijun/semi_supervised_knowledge_distillation
Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns Clustering
https://github.com/dzqjorking/transpose
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/e0015274/darknet
https://github.com/edgarjimenez1996/-fashion-mnist
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.