English

Deep Bayesian Active-Learning-to-Rank for Endoscopic Image Data

Computer Vision and Pattern Recognition 2022-08-08 v1

Abstract

Automatic image-based disease severity estimation generally uses discrete (i.e., quantized) severity labels. Annotating discrete labels is often difficult due to the images with ambiguous severity. An easier alternative is to use relative annotation, which compares the severity level between image pairs. By using a learning-to-rank framework with relative annotation, we can train a neural network that estimates rank scores that are relative to severity levels. However, the relative annotation for all possible pairs is prohibitive, and therefore, appropriate sample pair selection is mandatory. This paper proposes a deep Bayesian active-learning-to-rank, which trains a Bayesian convolutional neural network while automatically selecting appropriate pairs for relative annotation. We confirmed the efficiency of the proposed method through experiments on endoscopic images of ulcerative colitis. In addition, we confirmed that our method is useful even with the severe class imbalance because of its ability to select samples from minor classes automatically.

Keywords

Cite

@article{arxiv.2208.03020,
  title  = {Deep Bayesian Active-Learning-to-Rank for Endoscopic Image Data},
  author = {Takeaki Kadota and Hideaki Hayashi and Ryoma Bise and Kiyohito Tanaka and Seiichi Uchida},
  journal= {arXiv preprint arXiv:2208.03020},
  year   = {2022}
}

Comments

14 pages, 8 figures, accepted at MIUA 2022

R2 v1 2026-06-25T01:30:02.567Z