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

arXiv: https://arxiv.org/abs/1605.02697 · HTML: https://mlsanity.com/paper/1605.02697/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 May 2016.

## Built on by (most cited first, 7 of 7)

- [Explainability of deep vision-based autonomous driving systems: Review and challenges](https://mlsanity.com/paper/2101.05307/) (2021)
- [Interpretable by Design: Learning Predictors by Composing Interpretable Queries](https://mlsanity.com/paper/2207.00938/) (2022)
- [Robust Visual Question Answering: Datasets, Methods, and Future Challenges](https://mlsanity.com/paper/2307.11471/) (2023)
- [Contextualized Keyword Representations for Multi-modal Retinal Image Captioning](https://mlsanity.com/paper/2104.12471/) (2021)
- [Improving Visual Question Answering Models through Robustness Analysis and In-Context Learning with a Chain of Basic Questions](https://mlsanity.com/paper/2304.03147/) (2023)
- [Mobile Robots through Task-Based Human Instructions using Incremental Curriculum Learning](https://mlsanity.com/paper/2412.19159/) (2024)
- [Bridge Damage Cause Estimation Using Multiple Images Based on Visual Question Answering](https://mlsanity.com/paper/2302.09208/) (2023)

## Abstract (arXiv)

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.