Illusions in Humans and AI: How Visual Perception Aligns and Diverges
By: Jianyi Yang , Junyi Ye , Ankan Dash and more
Potential Business Impact:
Makes AI see like humans, but with new tricks.
By comparing biological and artificial perception through the lens of illusions, we highlight critical differences in how each system constructs visual reality. Understanding these divergences can inform the development of more robust, interpretable, and human-aligned artificial intelligence (AI) vision systems. In particular, visual illusions expose how human perception is based on contextual assumptions rather than raw sensory data. As artificial vision systems increasingly perform human-like tasks, it is important to ask: does AI experience illusions, too? Does it have unique illusions? This article explores how AI responds to classic visual illusions that involve color, size, shape, and motion. We find that some illusion-like effects can emerge in these models, either through targeted training or as by-products of pattern recognition. In contrast, we also identify illusions unique to AI, such as pixel-level sensitivity and hallucinations, that lack human counterparts. By systematically comparing human and AI responses to visual illusions, we uncover alignment gaps and AI-specific perceptual vulnerabilities invisible to human perception. These findings provide insights for future research on vision systems that preserve human-beneficial perceptual biases while avoiding distortions that undermine trust and safety.
Similar Papers
Leveraging Geometric Visual Illusions as Perceptual Inductive Biases for Vision Models
CV and Pattern Recognition
Teaches computers to see better using optical illusions.
Do Vision Transformers See Like Humans? Evaluating their Perceptual Alignment
CV and Pattern Recognition
Makes computers see like people, but bigger is worse.
From Images to Perception: Emergence of Perceptual Properties by Reconstructing Images
CV and Pattern Recognition
Computer sees images like humans do.