Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mao, Lingjun, Tang, Zineng, Suhr, Alane
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2412.06184
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913602423750656
author Mao, Lingjun
Tang, Zineng
Suhr, Alane
author_facet Mao, Lingjun
Tang, Zineng
Suhr, Alane
contents We study the perception of color illusions by vision-language models. Color illusion, where a person's visual system perceives color differently from actual color, is well-studied in human vision. However, it remains underexplored whether vision-language models (VLMs), trained on large-scale human data, exhibit similar perceptual biases when confronted with such color illusions. We propose an automated framework for generating color illusion images, resulting in RCID (Realistic Color Illusion Dataset), a dataset of 19,000 realistic illusion images. Our experiments show that all studied VLMs exhibit perceptual biases similar human vision. Finally, we train a model to distinguish both human perception and actual pixel differences.
format Preprint
id arxiv_https___arxiv_org_abs_2412_06184
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Evaluating Model Perception of Color Illusions in Photorealistic Scenes
Mao, Lingjun
Tang, Zineng
Suhr, Alane
Computer Vision and Pattern Recognition
We study the perception of color illusions by vision-language models. Color illusion, where a person's visual system perceives color differently from actual color, is well-studied in human vision. However, it remains underexplored whether vision-language models (VLMs), trained on large-scale human data, exhibit similar perceptual biases when confronted with such color illusions. We propose an automated framework for generating color illusion images, resulting in RCID (Realistic Color Illusion Dataset), a dataset of 19,000 realistic illusion images. Our experiments show that all studied VLMs exhibit perceptual biases similar human vision. Finally, we train a model to distinguish both human perception and actual pixel differences.
title Evaluating Model Perception of Color Illusions in Photorealistic Scenes
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.06184