# IQ-VQA: Intelligent Visual Question Answering

arXiv: https://arxiv.org/abs/2007.04422 · HTML: https://mlsanity.com/paper/2007.04422/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jul 2020.

## Built on by (most cited first, 4 of 4)

- [Benchmarking Spatial Relationships in Text-to-Image Generation](https://mlsanity.com/paper/2212.10015/) (2022)
- [Visual Question Answering: A Survey on Techniques and Common Trends in Recent Literature](https://mlsanity.com/paper/2305.11033/) (2023)
- [Consistency-preserving Visual Question Answering in Medical Imaging](https://mlsanity.com/paper/2206.13296/) (2022)
- [Logical Implications for Visual Question Answering Consistency](https://mlsanity.com/paper/2303.09427/) (2023)

## Abstract (arXiv)

Even though there has been tremendous progress in the field of Visual Question Answering, models today still tend to be inconsistent and brittle. To this end, we propose a model-independent cyclic framework which increases consistency and robustness of any VQA architecture. We train our models to answer the original question, generate an implication based on the answer and then also learn to answer the generated implication correctly. As a part of the cyclic framework, we propose a novel implication generator which can generate implied questions from any question-answer pair. As a baseline for future works on consistency, we provide a new human annotated VQA-Implications dataset. The dataset consists of ~30k questions containing implications of 3 types - Logical Equivalence, Necessary Condition and Mutual Exclusion - made from the VQA v2.0 validation dataset. We show that our framework improves consistency of VQA models by ~15% on the rule-based dataset, ~7% on VQA-Implications dataset and robustness by ~2%, without degrading their performance. In addition, we also quantitatively show improvement in attention maps which highlights better multi-modal understanding of vision and language.