Influence of Task on the Geometry of a Perceptual Space

Perceptual spaces are representations of a sensory or cognitive domain in which the domain’s elements correspond to points, and distances between these points are perceptual differences. Proximity relationships within a perceptual space can support a variety of functions, including discrimination, grouping, learning, and generalization. These diverse functions may use the features of the domain in different ways, resulting in task-dependent influences on the geometry of the space. To identify and characterize these influences, we focused on a domain of visual textures. These textures varied across many dimensions, including mean luminance and low- and high-order spatial correlations, which formed the axes of the space. Previous work characterized the geometry of this space with a threshold texture segmentation task: an approximately Euclidean distance that corresponded to the informativeness of the image statistics in natural images. However, when subjects are asked to make suprathreshold similarity judgments, the geometry of the space changes in two ways: greater weight was given to the higher-order local features (linear transformation), and axes became curved (nonlinear transformation). Here we report that the geometry undergoes further transformations with specific tasks: judging similarity based on brightness, judging similarity based on visual working memory, and grouping. These changes are consistent across subjects (N= 6) and primarily consist of linear transformations. This reformatting likely represents top-down influences on the gains of neural populations.