mlsanityData to 7 Oct 2026

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

arXiv 2303.10699 ↗First posted 19 Mar 2023cs.CL cs.CVcited by 4

Not on the map. Why?

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.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 17 of its 29 references that are in the map. First posted on arXiv 19 Mar 2023.

Builds on

17 of 29 references.

References · 17

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  6. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  7. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,498
  8. 2017Billion-scale similarity search with GPUscited by 2,477
  9. 2019OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledgecited by 1,114
  10. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
  11. 2022A-OKVQA: A Benchmark for Visual Question Answering using World Knowledgecited by 702
  12. 2016FVQA: Fact-based Visual Question Answeringcited by 181
5 more
  1. 2022Retrieval Augmented Visual Question Answering with Outside Knowledgecited by 93
  2. 2020Mucko: Multi-Layer Cross-Modal Knowledge Reasoning for Fact-based Visual Question Answeringcited by 51
  3. 2021Zero-shot Visual Question Answering using Knowledge Graphcited by 37
  4. 2021Select, Substitute, Search: A New Benchmark for Knowledge-Augmented Visual Question Answeringcited by 33
  5. 2020Sanitizing Synthetic Training Data Generation for Question Answering over Knowledge Graphscited by 4

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 0; 2025: 1.

4 papers.

  1. 2023Retrieving Multimodal Information for Augmented Generation: A Surveycited by 84
  2. 2023Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answeringcited by 51
  3. 2023From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunitiescited by 24
  4. 2025Augmented Vision-Language Models: A Systematic Reviewcited by 0