papers AI Learner
The Github is limit! Click to go to the new site.

Generalized Hadamard-Product Fusion Operators for Visual Question Answering

2018-04-06
Brendan Duke, Graham W. Taylor

Abstract

We propose a generalized class of multimodal fusion operators for the task of visual question answering (VQA). We identify generalizations of existing multimodal fusion operators based on the Hadamard product, and show that specific non-trivial instantiations of this generalized fusion operator exhibit superior performance in terms of OpenEnded accuracy on the VQA task. In particular, we introduce Nonlinearity Ensembling, Feature Gating, and post-fusion neural network layers as fusion operator components, culminating in an absolute percentage point improvement of $1.1\%$ on the VQA 2.0 test-dev set over baseline fusion operators, which use the same features as input. We use our findings as evidence that our generalized class of fusion operators could lead to the discovery of even superior task-specific operators when used as a search space in an architecture search over fusion operators.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1803.09374

PDF

https://arxiv.org/pdf/1803.09374


Similar Posts

Comments