VoQA: Visual-only Question Answering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: An, Jianing, Jiang, Luyang, Luo, Jie, Wu, Wenjun, Huang, Lei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914174230069248
author An, Jianing
Jiang, Luyang
Luo, Jie
Wu, Wenjun
Huang, Lei
author_facet An, Jianing
Jiang, Luyang
Luo, Jie
Wu, Wenjun
Huang, Lei
contents Visual understanding requires interpreting both natural scenes and the textual information that appears within them, motivating tasks such as Visual Question Answering (VQA). However, current VQA benchmarks overlook scenarios with visually embedded questions, whereas advanced agents should be able to see the question without separate text input as humans. We introduce Visual-only Question Answering (VoQA), where both the scene and the question appear within a single image, requiring models to perceive and reason purely through vision. This setting supports more realistic visual understanding and interaction in scenarios where questions or instructions are embedded directly in the visual scene. Evaluations under pure visual-only zero-shot, prompt-guided and OCR-assisted settings show that current models exhibit a clear performance drop compared to traditional VQA. To address this, we investigate question-alignment fine-tuning strategies designed to guide models toward interpreting the visual question prior to reasoning. Leveraging VoQA dataset together with these strategies yields robust vision-only reasoning while preserving cross-task generalization to traditional VQA, reflecting the complementary visual and textual reasoning capabilities fostered through VoQA training. The code and data are publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2505_14227
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VoQA: Visual-only Question Answering
An, Jianing
Jiang, Luyang
Luo, Jie
Wu, Wenjun
Huang, Lei
Computer Vision and Pattern Recognition
Artificial Intelligence
Visual understanding requires interpreting both natural scenes and the textual information that appears within them, motivating tasks such as Visual Question Answering (VQA). However, current VQA benchmarks overlook scenarios with visually embedded questions, whereas advanced agents should be able to see the question without separate text input as humans. We introduce Visual-only Question Answering (VoQA), where both the scene and the question appear within a single image, requiring models to perceive and reason purely through vision. This setting supports more realistic visual understanding and interaction in scenarios where questions or instructions are embedded directly in the visual scene. Evaluations under pure visual-only zero-shot, prompt-guided and OCR-assisted settings show that current models exhibit a clear performance drop compared to traditional VQA. To address this, we investigate question-alignment fine-tuning strategies designed to guide models toward interpreting the visual question prior to reasoning. Leveraging VoQA dataset together with these strategies yields robust vision-only reasoning while preserving cross-task generalization to traditional VQA, reflecting the complementary visual and textual reasoning capabilities fostered through VoQA training. The code and data are publicly available.
title VoQA: Visual-only Question Answering
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2505.14227