SMSP: A Plug-and-Play Strategy of Multi-Scale Perception for MLLMs to Perceive Visual Illusions

Read full text Summarise with VIRAT
Authors: Jinzhe Tu, Ruilei Guo, Zihan Guo, Junxiao Yang, Shiyao Cui, Minlie Huang
Cited by: 0
References: 29

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Recent studies have shown that multimodal large language models (MLLMs) are highly vulnerable to hidden-pattern visual illusions, where the hidden content is imperceptible to models but obvious to humans. This deficiency highlights a perceptual misalignment between current MLLMs and humans, and also introduces potential safety concerns. To systematically investigate this failure, we introduce IlluChar, a comprehensive and challenging illusion dataset, and uncover a key underlying mechanism for the models' failure: high-frequency attention bias, where the models are easily distracted by high-frequency background textures in illusion images, causing them to overlook hidden patterns. To address this issue, we propose the Strategy of Multi-Scale Perception (SMSP), a plug-and-play framework that aligns with human visual perceptual strategies. By suppressing distracting high-frequency background signals, SMSP generates images closer to human perception. Our experiments demonstrate that SMSP significantly improves the performance of all evaluated MLLMs on illusion images, for instance, increasing the accuracy of Qwen3-VL-8B-Instruct from 13.0% to 84.0%. Our work provides novel insights into MLLMs' visual perception, and offers a practical and robust solution to enhance it.

Fields of Study & Subjects

Multimodal Machine Learning Applications Advanced Neural Network Applications Visual Attention and Saliency Detection

Publication details

Journal / source
ACM International Conference on Multimedia (ACM MM)
Pages
9735–9743
Publication date
6 November 2026
Language
EN