# Generative Visual Question Answering

arXiv: https://arxiv.org/abs/2307.10405 · HTML: https://mlsanity.com/paper/2307.10405/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 8 references that are in the map.
- First posted on arXiv 18 Jul 2023.

## Builds on (most cited first, 8 of 8)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [Mind the Gap: Assessing Temporal Generalization in Neural Language Models](https://mlsanity.com/paper/2102.01951/) (2021)
- [Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing](https://mlsanity.com/paper/1912.07538/) (2019)
- [Cycle-Consistency for Robust Visual Question Answering](https://mlsanity.com/paper/1902.05660/) (2019)
- [Adversarial VQA: A New Benchmark for Evaluating the Robustness of VQA Models](https://mlsanity.com/paper/2106.00245/) (2021)
- [Exploring The Landscape of Distributional Robustness for Question Answering Models](https://mlsanity.com/paper/2210.12517/) (2022)

## Built on by (most cited first, 1 of 1)

- [EVLM: Self-Reflective Multimodal Reasoning for Cross-Dimensional Visual Editing](https://mlsanity.com/paper/2412.10566/) (2024)

## Abstract (arXiv)

Multi-modal tasks involving vision and language in deep learning continue to rise in popularity and are leading to the development of newer models that can generalize beyond the extent of their training data. The current models lack temporal generalization which enables models to adapt to changes in future data. This paper discusses a viable approach to creating an advanced Visual Question Answering (VQA) model which can produce successful results on temporal generalization. We propose a new data set, GenVQA, utilizing images and captions from the VQAv2 and MS-COCO dataset to generate new images through stable diffusion. This augmented dataset is then used to test a combination of seven baseline and cutting edge VQA models. Performance evaluation focuses on questions mirroring the original VQAv2 dataset, with the answers having been adjusted to the new images. This paper's purpose is to investigate the robustness of several successful VQA models to assess their performance on future data distributions. Model architectures are analyzed to identify common stylistic choices that improve generalization under temporal distribution shifts. This research highlights the importance of creating a large-scale future shifted dataset. This data can enhance the robustness of VQA models, allowing their future peers to have improved ability to adapt to temporal distribution shifts.