# Visual Question Answering as a Multi-Task Problem

Source: [Visual Question Answering as a Multi-Task Problem](<https://www.sota2.com/research/paper/68fa67d31e209131cea18b4d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:43.424Z

Authors: Amelia Elizabeth Pollard, Jonathan L. Shapiro

Published: 2020-07-03T16:07:13.000Z

## Abstract

Visual Question Answering(VQA) is a highly complex problem set, relying on many sub-problems to produce reasonable answers. In this paper, we present the hypothesis that Visual Question Answering should be viewed as a multi-task problem, and provide evidence to support this hypothesis. We demonstrate this by reformatting two commonly used Visual Question Answering datasets, COCO-QA and DAQUAR, into a multi-task format and train these reformatted datasets on two baseline networks, with one designed specifically to eliminate other possible causes for performance changes as a result of the reformatting. Though the networks demonstrated in this paper do not achieve strongly competitive results, we find that the multi-task approach to Visual Question Answering results in increases in performance of 5-9% against the single-task formatting, and that the networks reach convergence much faster than in the single-task case. Finally we discuss possible reasons for the observed difference in performance, and perform additional experiments which rule out causes not associated with the learning of the dataset as a multi-task problem.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2007.01780>)

[PDF](<https://arxiv.org/pdf/2007.01780.pdf>)