Beyond OCR Accuracy: Text-Centric VQA Under Image Degradation with Modular and End-to-End

2026-09-12

AI Summary

研究对比了模块化OCR管道与端到端视觉-语言模型在图像降质条件下的文本中心VQA任务表现，发现模块化方法更鲁棒。

Abstract

Text-centric Visual Question Answering (VQA) requires reading and reasoning over text embedded in images, a task made substantially harder when images suffer from real-world degradation such as motion blur, low resolution, or compression artifacts. While modular OCR-based pipelines and end-to-end vision-language models are both widely used for this task, their comparative robustness under degraded conditions remains underexplored. We present an empirical study comparing two modular pipelines with SA-DBNet, a custom detector architecture combining ResNet-18 with self-attention spatial modeling and deformable convolutions against an end-to-end vision-language baseline, evaluated on 4013 degraded images with 7000 question-answer pairs. Fine-tuned modular pipelines achieve up to 57.50% exact-match accuracy versus 38.00% for the end-to-end baseline, with domain-specific fine-tuning yielding a gain of up to 29.50 percentage points. Critically, we find that conventional OCR error metrics like Character Error Rate and Word Error Rate are unreliable predictors of downstream VQA performance, as semantic reasoning can compensate for recognition failures when contextual cues are present. These findings highlight the importance of task-aware evaluation for text-centric VQA systems under realistic visual conditions. Codes are available here

Problem

• Text-centric VQA
• Image Degradation
• OCR Accuracy
• Vision-Language Models
• Degraded Conditions

Innovation

• modular OCR pipelines
• end-to-end vision-language models
• degraded images
• task-aware evaluation
• semantic reasoning