SemVink: Advancing VLMs' Semantic Understanding of Optical Illusions via Visual Global Thinking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Sifan, Cai, Yujun, Wang, Yiwei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911210487676928
author Li, Sifan
Cai, Yujun
Wang, Yiwei
author_facet Li, Sifan
Cai, Yujun
Wang, Yiwei
contents Vision-language models (VLMs) excel in semantic tasks but falter at a core human capability: detecting hidden content in optical illusions or AI-generated images through perceptual adjustments like zooming. We introduce HC-Bench, a benchmark of 112 images with hidden text, objects, and illusions, revealing that leading VLMs achieve near-zero accuracy (0-5.36%)-even with explicit prompting. Humans resolve such ambiguities instinctively, yet VLMs fail due to an overreliance on high-level semantics. Strikingly, we propose SemVink (Semantic Visual Thinking) by simply scaling images to low resolutions (32-128 pixels), which unlocks >99% accuracy by eliminating redundant visual noise. This exposes a critical architectural flaw: VLMs prioritize abstract reasoning over low-level visual operations crucial for real-world robustness. Our work urges a shift toward hybrid models integrating multi-scale processing, bridging the gap between computational vision and human cognition for applications in medical imaging, security, and beyond.
format Preprint
id arxiv_https___arxiv_org_abs_2506_02803
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SemVink: Advancing VLMs' Semantic Understanding of Optical Illusions via Visual Global Thinking
Li, Sifan
Cai, Yujun
Wang, Yiwei
Computation and Language
Computer Vision and Pattern Recognition
Vision-language models (VLMs) excel in semantic tasks but falter at a core human capability: detecting hidden content in optical illusions or AI-generated images through perceptual adjustments like zooming. We introduce HC-Bench, a benchmark of 112 images with hidden text, objects, and illusions, revealing that leading VLMs achieve near-zero accuracy (0-5.36%)-even with explicit prompting. Humans resolve such ambiguities instinctively, yet VLMs fail due to an overreliance on high-level semantics. Strikingly, we propose SemVink (Semantic Visual Thinking) by simply scaling images to low resolutions (32-128 pixels), which unlocks >99% accuracy by eliminating redundant visual noise. This exposes a critical architectural flaw: VLMs prioritize abstract reasoning over low-level visual operations crucial for real-world robustness. Our work urges a shift toward hybrid models integrating multi-scale processing, bridging the gap between computational vision and human cognition for applications in medical imaging, security, and beyond.
title SemVink: Advancing VLMs' Semantic Understanding of Optical Illusions via Visual Global Thinking
topic Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.02803