2024/12/07 by Tomer Ullman, Ullman, Tomer · 3 voices · 8 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Psychology · Social Sciences · #African history and culture analysis #Cognitive psychology #Computer science #Computer vision #Illusion #Optical illusion #Psychology #cs.CL #cs.CV #q-bio.NC
paper · pdf · doi:10.48550/arxiv.2412.18613
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2024/12/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Illusions are entertaining, but they are also a useful diagnostic tool in cognitive science, philosophy, and neuroscience. A typical illusion shows a gap between how something `really is' and how something `appears to be', and this gap helps us understand the mental processing that led to how something appears to be. Illusions are also useful for investigating artificial systems, and much research has examined whether computational models of perception fall prey to the same illusions as people. Here, I invert the standard use of perceptual illusions to examine basic processing errors in current vision language models. I present these models with illusory-illusions, neighbors of common illusions that should not elicit processing errors. These include such things as perfectly reasonable ducks, crooked lines that truly are crooked, circles that seem to have different sizes because they are, in fact, of different sizes, and so on. I show that many current vision language systems mistakenly see these illusion-illusions as illusions. I suggest that such failures are part of broader failures already discussed in the literature.