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

TL;DR

This study develops a multi-task neural model that learns various quantification mechanisms from visual scenes, demonstrating improved accuracy and generalization, while reflecting human-like cognitive interference effects.

Contribution

It introduces a multi-task learning approach to jointly model set comparison, vague quantification, and proportional estimation from visual data, a novel integration inspired by human cognition.

Findings

Multi-task learning improves proportional estimation accuracy.

The model generalizes to unseen object combinations.

Interference effects mirror human cognitive patterns.

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.