通过降低图像细节，让视觉模型更聚焦关键结构，提升问答准确率。
Less Detail, Better Answers: Degradation-Driven Prompting for VQA
- 用降采样和结构提示强制模型忽略干扰细节
- 在复杂视觉任务中准确率提升，最高达12.3%相对改进
- 适合需要可靠推理的高精度视觉问答场景
视觉语言模型在视觉问答任务上取得显著进展，但高分辨率细节常成为噪声，导致幻觉或推理错误。本文提出退化驱动提示（DDP）框架，通过有策略地降低图像保真度，引导模型聚焦核心结构信息。在两类任务中评估：物理属性任务针对人类易误判图像，采用80p降采样、白底掩码与正交线等结构视觉辅助，并结合上下文学习（ICL）校准模型关注点；感知现象任务涵盖机器敏感的视觉异常与错觉，包括视觉异常（VA）、颜色（CI）、运动（MI）、格式塔（GI）、几何（GSI）及视觉幻觉（VI），采用任务分类阶段与模糊掩码、对比度增强等专用工具协同降采样。实验表明，通过有意退化输入并提供结构化提示，可有效避开干扰纹理，在挑战性视觉基准上实现更优推理准确率。
原文摘要 · Abstract (English)
Recent advancements in Vision-Language Models (VLMs) have significantly pushed the boundaries of Visual Question Answering (VQA).However,high-resolution details can sometimes become noise that leads to hallucinations or reasoning errors. In this paper,we propose Degradation-Driven Prompting (DDP), a novel framework that improves VQA performance by strategically reducing image fidelity to force models to focus on essential structural information. We evaluate DDP across two distinct tasks. Physical attributes targets images prone to human misjudgment, where DDP employs a combination of 80p downsampling, structural visual aids (white background masks and orthometric lines), and In-Context Learning (ICL) to calibrate the model's focus. Perceptual phenomena addresses various machine-susceptible visual anomalies and illusions, including Visual Anomaly (VA), Color (CI), Motion(MI),Gestalt (GI), Geometric (GSI), and Visual Illusions (VI).For this task, DDP integrates a task-classification stage with specialized tools such as blur masks and contrast enhancement alongside downsampling. Our experimental results demonstrate that less is more: by intentionally degrading visual inputs and providing targeted structural prompts, DDP enables VLMs to bypass distracting textures and achieve superior reasoning accuracy on challenging visual benchmarks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。