Back to search

University of Waterloo

Size Constraints in Segmentation and Size Predictions

Abstract

dc:description.abstract

Segment size, which one may equivalently refer to as volume, area, or cardinality, is uniquely defined by segmentation, e.g. by aggregating pixel-level predictions. On the other hand, size provides only a very weak constraint on segmentation. However, as this thesis observes, explicit size constraints are powerful cues for training segmentation models in weakly supervised settings, e.g. when only image-level class tags are provided or a fraction of pixels is labeled. We also observe that some standard unsupervised losses may have implicit size bias resulting in notable segmentation artifacts. This thesis addresses three closely related problems regarding size constraints in segmentation and size predictions. First, we propose explicit size targets for training segmentation models without ground truth masks. We show approximate size targets predicted by human annotators result in segmentation quality on par with full pixel-precise supervision. The second contribution of this thesis is to show implicit size bias in standard unsupervised segmentation losses common in scribble supervision, e.g. mutual information or the Potts model. We show that this bias leads to the performance collapse as the amount of scribbles decreases. In contrast, our size-target supervision works well without any scribbles. Lastly, inspired by the enhanced segmentation outcomes achieved through size-target supervision, we explore the potential of deep models in predicting sizes directly.

Degree

thesis:*
Grantor dc:publisher
University of Waterloo
Year dc:date.issued
2024

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Fan, Xingye
Advisor dc:contributor.advisor
  • Boykov, Yuri

Subjects

dc:subject × 3

Rights

Language dc:language.iso
en

Identifiers

dc:identifier.*
Handle dc:identifier.uri
http://hdl.handle.net/10012/20543

Chain of custody

source
Harvested from
University of Waterloo
Base URL
dspacemainprd01.lib.uwaterloo.ca/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Fan, Xingye. Size Constraints in Segmentation and Size Predictions. University of Waterloo, 2024. http://hdl.handle.net/10012/20543