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

Learning to Count Objects in Natural Images for Visual Question Answering

2018-02-15
Yan Zhang, Jonathon Hare, Adam Prügel-Bennett

Abstract

Visual Question Answering (VQA) models have struggled with counting objects in natural images so far. We identify a fundamental problem due to soft attention in these models as a cause. To circumvent this problem, we propose a neural network component that allows robust counting from object proposals. Experiments on a toy task show the effectiveness of this component and we obtain state-of-the-art accuracy on the number category of the VQA v2 dataset without negatively affecting other categories, even outperforming ensemble models with our single model. On a difficult balanced pair metric, the component gives a substantial improvement in counting over a strong baseline by 6.6%.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1802.05766

PDF

https://arxiv.org/pdf/1802.05766


Similar Posts

Comments