English

Comparatives, Quantifiers, Proportions: A Multi-Task Model for the Learning of Quantities from Vision

Computer Vision and Pattern Recognition 2018-04-16 v1 Machine Learning Machine Learning

Abstract

The present work investigates whether different quantification mechanisms (set comparison, vague quantification, and proportional estimation) can be jointly learned from visual scenes by a multi-task computational model. The motivation is that, in humans, these processes underlie the same cognitive, non-symbolic ability, which allows an automatic estimation and comparison of set magnitudes. We show that when information about lower-complexity tasks is available, the higher-level proportional task becomes more accurate than when performed in isolation. Moreover, the multi-task model is able to generalize to unseen combinations of target/non-target objects. Consistently with behavioral evidence showing the interference of absolute number in the proportional task, the multi-task model no longer works when asked to provide the number of target objects in the scene.

Keywords

Cite

@article{arxiv.1804.05018,
  title  = {Comparatives, Quantifiers, Proportions: A Multi-Task Model for the Learning of Quantities from Vision},
  author = {Sandro Pezzelle and Ionut-Teodor Sorodoc and Raffaella Bernardi},
  journal= {arXiv preprint arXiv:1804.05018},
  year   = {2018}
}

Comments

12 pages (references included). To appear in the Proceedings of NAACL-HLT 2018

R2 v1 2026-06-23T01:23:08.389Z