• Home
  • Search
  • Deconfounded Visual Question Generation with Causal Inference
  • Cite Icon8
  • https://doi.org/10.1145/3581783.3612536Copy DOI Icon

Deconfounded Visual Question Generation with Causal Inference

  • Oct 26, 2023
  • Jiali Chen +4 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Visual Question Generation (VQG) task aims to generate meaningful and logically reasonable questions about the given image targeting an answer. Existing methods mainly focus on the visual concepts present in the image for question generation and have shown remarkable performance in VQG. However, these models frequently learn highly co-occurring object relationships and attributes, which is an inherent bias in question generation. This previously overlooked bias causes models to over-exploit the spurious correlations among visual features, the target answer, and the question. Therefore, they may generate inappropriate questions that contradict the visual content or facts. In this paper, we first introduce a causal perspective on VQG and adopt the causal graph to analyze spurious correlations among variables. Building on the analysis, we propose a Knowledge Enhanced Causal Visual Question Generation (KECVQG) model to mitigate the impact of spurious correlations in question generation. Specifically, an interventional visual feature extractor (IVE) is introduced in KECVQG, which aims to obtain unbiased visual features by disentangling. Then a knowledge-guided representation extractor (KRE) is employed to align unbiased features with external knowledge. Finally, the output features from KRE are sent into a standard transformer decoder to generate questions. Extensive experiments on the VQA v2.0 and OKVQA datasets show that KECVQG significantly outperforms existing models.

Similar Papers
  • Research Article
  • Citations4

Diverse Visual Question Generation Based on Multiple Objects Selection

  • Mar 08, 2024
  • ACM Transactions on Multimedia Computing, Communications, and Applications
  • Wenhao Fang +4
  • Book Chapter

Task-Based Ontology Evaluation for Question Generation

  • Oct 21, 2025
  • Frontiers in artificial intelligence and applications
  • Samah Alkhuzaey +3
  • Conference Article
  • Citations4

UAV-VQG: Visual Question Generation Framework on UAV Images

  • Dec 15, 2021
  • Argho Sarkar +1
  • Conference Article
  • Citations9

K-VQG: Knowledge-aware Visual Question Generation for Common-sense Acquisition

  • Jan 01, 2023
  • Kohei Uehara +1
  • Dissertation

Automatic question generation from natural language texts

  • Jan 01, 2022
  • Zhen Cao
  • Book Chapter
  • Citations6

How Question Generation Can Help Question Answering over Knowledge Base

  • Jan 01, 2019
  • Sen Hu +2
  • Book Chapter
  • Citations1

Automated Question Generation and Answer Verification Using Visual Data

  • Jan 01, 2020
  • Shrey Nahar +4
  • Supplementary Content
  • Citations114

Automatic question generation: a review of methodologies, datasets, evaluation metrics, and applications

  • Jan 01, 2023
  • Progress in Artificial Intelligence
  • Nikahat Mulla +1
  • Research Article
  • Citations1

ConVQG: Contrastive Visual Question Generation with Multimodal Guidance

  • Mar 24, 2024
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Li Mi +5
  • Conference Article

Learning to Ask: Multi-Decoder Fine-Tuning for Multi-Hop Visual Question Generation with External Knowledge

  • Jan 01, 2026
  • Arpan Phukan +2
  • Research Article
  • Citations6

Explicitly diverse visual question generation.

  • Apr 01, 2025
  • Neural networks : the official journal of the International Neural Network Society
  • Jiayuan Xie +4
  • Research Article

An approach to medical visual question generation based on question categories

  • Oct 16, 2025
  • Journal of the Chinese Institute of Engineers
  • N Sheerin Sitara +3
  • Book Chapter

Visual Question Generation Under Multi-granularity Cross-Modal Interaction

  • Jan 01, 2023
  • Zi Chai +3
  • Research Article
  • Citations4

Ask Questions With Double Hints: Visual Question Generation With Answer-Awareness and Region-Reference.

  • Dec 01, 2024
  • IEEE transactions on pattern analysis and machine intelligence
  • Kai Shen +6
  • Research Article
  • Citations27

Knowledge-Based Visual Question Generation

  • Nov 01, 2022
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Jiayuan Xie +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.