English

Expected exponential loss for gaze-based video and volume ground truth annotation

Computer Vision and Pattern Recognition 2017-07-18 v1

Abstract

Many recent machine learning approaches used in medical imaging are highly reliant on large amounts of image and ground truth data. In the context of object segmentation, pixel-wise annotations are extremely expensive to collect, especially in video and 3D volumes. To reduce this annotation burden, we propose a novel framework to allow annotators to simply observe the object to segment and record where they have looked at with a $200 eye gaze tracker. Our method then estimates pixel-wise probabilities for the presence of the object throughout the sequence from which we train a classifier in semi-supervised setting using a novel Expected Exponential loss function. We show that our framework provides superior performances on a wide range of medical image settings compared to existing strategies and that our method can be combined with current crowd-sourcing paradigms as well.

Keywords

Cite

@article{arxiv.1707.04905,
  title  = {Expected exponential loss for gaze-based video and volume ground truth annotation},
  author = {Laurent Lejeune and Mario Christoudias and Raphael Sznitman},
  journal= {arXiv preprint arXiv:1707.04905},
  year   = {2017}
}

Comments

9 pages, 5 figues, MICCAI 2017 - LABELS Workshop

R2 v1 2026-06-22T20:48:20.202Z