基于 illusion 意识的视觉预处理与反 illusion 提示的经典 illusion 理解在视觉-语言模型中的应用
Illusion-Aware Visual Preprocessing and Anti-Illusion Prompting for Classic Illusion Understanding in Vision-Language Models
AI总结：
本文提出无需训练的框架，通过图像预处理、反 illusion 提示工程和多票集成策略，解决视觉-语言模型对视觉错觉的感知与记忆冲突，实现90.48%和98.41%的准确率。
摘要：
视觉-语言模型（VLMs）对视觉错觉存在系统性偏差，倾向于回忆记忆事实而非感知实际视觉差异。本文提出一个无需训练的框架，用于2026年CVPR挑战任务1，通过三种互补策略解决感知与记忆冲突：（1）基于类型特异变换的错觉意识图像预处理，通过边缘提取、颜色隔离、形态学处理和参考线叠加削弱错觉诱导上下文；（2）反错觉提示工程引导VLMs进行定性视觉比较；（3）多票集成进一步提升鲁棒性。我们的方法在官方630张图像测试集上使用Claude（claude-opus-4-6）和5票多数集成达到90.48%的准确率，在人工验证子集上达到98.41%的准确率。该方法无需微调，仅依赖视觉操作和提示设计。我们的解决方案在挑战中获得第二名，仅比第一名低0.47%。代码可在https://github.com/jasminezz/sf-illusion-aware-vlm.git获取。
英文摘要：
Vision-Language Models (VLMs) exhibit systematic bias toward visual illusions, recalling memorized facts rather than perceiving actual visual differences. This paper presents a training-free framework for the 5th DataCV Challenge Task 1 at CVPR 2026, addressing this perception-versus-memory conflict through three complementary strategies:(1) illusion-aware image preprocessing that weakens illusion-inducing context via type-specific transformations (edge extraction, color isolation, morphological processing, and reference-line overlay), (2) anti-illusion prompt engineering guiding VLMs toward qualitative visual comparison, and (3) multi-vote ensemble that further improves robustness. Our method achieves 90.48% accuracy on the official 630-image test set using Claude (claude-opus-4-6) with 5-vote majority ensemble, and 98.41% on a human-verified subset. The approach requires no finetuning, relying solely on visual manipulation and prompt design. Our solution secured 2nd place in the challenge, only 0.47% behind the 1st-place solution. Code is available at https://github.com/jasminezz/sf-illusion-aware-vlm.git.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
