Active learning for segmentation based on Bayesian sample queries
作者：
Highlights：
• Bayesian sampling with information maximizing autoencoders for active learning.
• Task agnostic representation sampling combined with task oriented uncertainty.
• Iterative rapid coverage of a subset distribution with the full set in latent space.
• Quantify representational power of a sample from a large high dimensional dataset.
• High segmentation performance with only a small subset of the dataset been annotated.
摘要
•Bayesian sampling with information maximizing autoencoders for active learning.•Task agnostic representation sampling combined with task oriented uncertainty.•Iterative rapid coverage of a subset distribution with the full set in latent space.•Quantify representational power of a sample from a large high dimensional dataset.•High segmentation performance with only a small subset of the dataset been annotated.
论文关键词：Active learning,Bayesian inference,Representation learning
论文评审过程：Received 27 December 2019, Revised 29 June 2020, Accepted 12 October 2020, Available online 26 November 2020, Version of Record 11 January 2021.
论文官网地址：https://doi.org/10.1016/j.knosys.2020.106531
