# FVQA 2.0: Introducing Adversarial Samples into Fact-based Visual Question Answering

arXiv: https://arxiv.org/abs/2303.10699 · HTML: https://mlsanity.com/paper/2303.10699/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 29 references that are in the map.
- First posted on arXiv 19 Mar 2023.

## Builds on (most cited first, 17 of 17)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge](https://mlsanity.com/paper/2206.01718/) (2022)
- [FVQA: Fact-based Visual Question Answering](https://mlsanity.com/paper/1606.05433/) (2016)
- [Retrieval Augmented Visual Question Answering with Outside Knowledge](https://mlsanity.com/paper/2210.03809/) (2022)
- [Mucko: Multi-Layer Cross-Modal Knowledge Reasoning for Fact-based Visual Question Answering](https://mlsanity.com/paper/2006.09073/) (2020)
- [Zero-shot Visual Question Answering using Knowledge Graph](https://mlsanity.com/paper/2107.05348/) (2021)
- [Select, Substitute, Search: A New Benchmark for Knowledge-Augmented Visual Question Answering](https://mlsanity.com/paper/2103.05568/) (2021)
- [Sanitizing Synthetic Training Data Generation for Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2009.04915/) (2020)

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

- [Retrieving Multimodal Information for Augmented Generation: A Survey](https://mlsanity.com/paper/2303.10868/) (2023)
- [Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering](https://mlsanity.com/paper/2309.17133/) (2023)
- [From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities](https://mlsanity.com/paper/2311.00308/) (2023)
- [Augmented Vision-Language Models: A Systematic Review](https://mlsanity.com/paper/2507.22933/) (2025)

## Abstract (arXiv)

The widely used Fact-based Visual Question Answering (FVQA) dataset contains visually-grounded questions that require information retrieval using common sense knowledge graphs to answer. It has been observed that the original dataset is highly imbalanced and concentrated on a small portion of its associated knowledge graph. We introduce FVQA 2.0 which contains adversarial variants of test questions to address this imbalance. We show that systems trained with the original FVQA train sets can be vulnerable to adversarial samples and we demonstrate an augmentation scheme to reduce this vulnerability without human annotations.