Enacted Visual Perception: A Computational Model based on Piaget Equilibrium
This work addresses the challenge of integrating action and perception in computational models for AI and cognitive science, though it appears incremental as it builds on existing CNN architectures.
The paper tackles the problem of modeling visual perception as an active process by proposing a computational model based on Piaget's equilibrium, which adapts CNN filters via a high-level control signal to reflect thoughtful activity, resulting in enhanced filter performance.
In Maurice Merleau-Ponty's phenomenology of perception, analysis of perception accounts for an element of intentionality, and in effect therefore, perception and action cannot be viewed as distinct procedures. In the same line of thinking, Alva Noë considers perception as a thoughtful activity that relies on capacities for action and thought. Here, by looking into psychology as a source of inspiration, we propose a computational model for the action involved in visual perception based on the notion of equilibrium as defined by Jean Piaget. In such a model, Piaget's equilibrium reflects the mind's status, which is used to control the observation process. The proposed model is built around a modified version of convolutional neural networks (CNNs) with enhanced filter performance, where characteristics of filters are adaptively adjusted via a high-level control signal that accounts for the thoughtful activity in perception. While the CNN plays the role of the visual system, the control signal is assumed to be a product of mind.