2024/10/23 by Pablo Hernández-Cámara, Paula Daudén-Oliver, Valero Laparra +1 · 1 voice · 4 citations
Environmental Science · Neuroscience · Physics and Astronomy · Psychology · #Artificial intelligence #Color Science and Applications #Color constancy #Color vision #Computer science #Computer vision #Human visual system model #Image (mathematics) #Pattern recognition (psychology) #Perception #Psychology #Psychophysics #Remote Sensing in Agriculture #Segmentation #Set (abstract data type) #Similarity (geometry) #Standard illuminant #Visual perception and processing mechanisms #sort
paper · pdf · doi:10.3389/fpsyg.2024.1415958
published in Frontiers in Psychology 15, 1415958 (Frontiers Media)
openalex publication_date 2024/10/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01
The experiments allowed by current machine learning models imply a revival of the debate on the causes of specific trends of human visual psychophysics. Machine learning facilitates the exploration of the effect of specific visual goals (such as image segmentation) by different neural architectures in different statistical environments in an unprecedented manner. In this way, (1) the principles behind psychophysical facts such as the non-Euclidean nature of human color discrimination and (2) the emergence of human-like behaviour in artificial systems can be explored under a new light. In this work, we show for the first time that the tolerance or invariance of image segmentation networks for natural images under changes of illuminant in the color space (a sort of insensitivity region around the white ) is an ellipsoid oriented similarly to a (human) MacAdam ellipse. This striking similarity between an artificial system and human vision motivates a set of experiments checking the relevance of the statistical environment on the emergence of such insensitivity regions. Results suggest, that in this case, the statistics of the environment may be more relevant than the architecture selected to perform the image segmentation.