Ask Your Neurons: A Deep Learning Approach to Visual Question Answering

TL;DR

This paper introduces 'Ask Your Neurons', a deep learning model for visual question answering that combines image and language understanding, analyzes human consensus, and improves performance on the DAQUAR dataset.

Contribution

It presents a scalable end-to-end multi-modal model for visual question answering and introduces new metrics and datasets to analyze human consensus and model performance.

Findings

Strong model performance using global image representations

Analysis of language-only information with a new human baseline

Enhanced dataset with consensus answers improves evaluation

Abstract

We address a question answering task on real-world images that is set up as a Visual Turing Test. By combining latest advances in image representation and natural language processing, we propose Ask Your Neurons, a scalable, jointly trained, end-to-end formulation to this problem. In contrast to previous efforts, we are facing a multi-modal problem where the language output (answer) is conditioned on visual and natural language inputs (image and question). We provide additional insights into the problem by analyzing how much information is contained only in the language part for which we provide a new human baseline. To study human consensus, which is related to the ambiguities inherent in this challenging task, we propose two novel metrics and collect additional answers which extend the original DAQUAR dataset to DAQUAR-Consensus. Moreover, we also extend our analysis to VQA, a large-scale question answering about images dataset, where we investigate some particular design choices and show the importance of stronger visual models. At the same time, we achieve strong performance of our model that still uses a global image representation. Finally, based on such analysis, we refine our Ask Your Neurons on DAQUAR, which also leads to a better performance on this challenging task.