The Selectivity and Competition of the Mind's Eye in Visual Perception
This work addresses the unknown mechanisms by which the primary visual system directs information to higher brain levels, offering a new perspective for neuroscientists and a competitive classification framework for computer vision researchers.
The paper proposes a novel computational model incorporating lateral and top-down feedback through hierarchical competition to mimic high-level neural mechanisms of perception. This model not only explains information flow and selectivity in the brain but also forms a classification framework that rivals traditional supervised learning in computer vision.
Research has shown that neurons within the brain are selective to certain stimuli. For example, the fusiform face area (FFA) region is known by neuroscientists to selectively activate when people see faces over non-face objects. However, the mechanisms by which the primary visual system directs information to the correct higher levels of the brain are currently unknown. In our work, we mimic several high-level neural mechanisms of perception by creating a novel computational model that incorporates lateral and top down feedback in the form of hierarchical competition. Not only do we show that these elements can help explain the information flow and selectivity of high level areas within the brain, we also demonstrate that these neural mechanisms provide the foundation of a novel classification framework that rivals traditional supervised learning in computer vision. Additionally, we present both quantitative and qualitative results that demonstrate that our generative framework is consistent with neurological themes and enables simple, yet robust category level classification.