@inproceedings{bc012955a53549789a517708e8562c92,
title = "What{\textquoteright}s the point: Semantic segmentation with point supervision",
abstract = "The semantic image segmentation task presents a trade-off between test time accuracy and training time annotation cost. Detailed per-pixel annotations enable training accurate models but are very timeconsuming to obtain; image-level class labels are an order of magnitude cheaper but result in less accurate models. We take a natural step from image-level annotation towards stronger supervision: we ask annotators to point to an object if one exists. We incorporate this point supervision along with a novel objectness potential in the training loss function of a CNN model. Experimental results on the PASCAL VOC 2012 benchmark reveal that the combined effect of point-level supervision and objectness potential yields an improvement of 12.9% mIOU over image-level supervision. Further, we demonstrate that models trained with pointlevel supervision are more accurate than models trained with image-level, squiggle-level or full supervision given a fixed annotation budget.",
keywords = "Data annotation, Semantic segmentation, Weak supervision",
author = "Amy Bearman and Olga Russakovsky and Vittorio Ferrari and Li Fei-Fei",
note = "Publisher Copyright: {\textcopyright} Springer International Publishing AG 2016.; 14th European Conference on Computer Vision, ECCV 2016 ; Conference date: 08-10-2016 Through 16-10-2016",
year = "2016",
doi = "10.1007/978-3-319-46478-7_34",
language = "English (US)",
isbn = "9783319464770",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "549--565",
editor = "Bastian Leibe and Jiri Matas and Nicu Sebe and Max Welling",
booktitle = "Computer Vision - 14th European Conference, ECCV 2016, Proceedings",
address = "Germany",
}