Model-Centric and Data-Centric Aspects of Active Learning for Deep Neural Networks
Paper i proceeding, 2021

We study different aspects of active learning with deep neural networks in a consistent and unified way. i) We investigate incremental and cumulative training modes which specify how the newly labeled data are used for training. ii) We study active learning w.r.t. the model configurations such as the number of epochs and neurons as well as the choice of batch size. iii) We consider in detail the behavior of query strategies and their corresponding informativeness measures and accordingly propose more efficient querying procedures. iv) We perform statistical analyses, e.g., on actively learned classes and test error estimation, that reveal several insights about active learning. v) We investigate how active learning with neural networks can benefit from pseudo-labels as proxies for actual labels.


John Daniel Bossér

Linköpings universitet

Erik Sorstadius

Student vid Chalmers

Morteza Haghir Chehreghani

Data Science och AI 1

Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021

9781665439022 (ISBN)

2021 IEEE International Conference on Big Data, Big Data 2021
Virtual, Online, USA,



Transportteknik och logistik

Bioinformatik (beräkningsbiologi)



Mer information

Senast uppdaterat