Neural Mechanisms for Form and Motion Detection and Integration: Biology Meets Machine Vision

Abstract. General-purpose vision systems, either biological or techni-cal, rely on the robust processing of visual data from the sensor array. Such systems need to adapt their processing capabilities to varying con-ditions, have to deal with noise, and also need to learn task-relevant representations. Here, we describe models of early and mid-level vision. These models are motivated by the layered and hierarchical processing of form and motion information in primate cortex. Core cortical pro-cessing principles are: (i) bottom-up processing to build representations of increasing feature specificity and spatial scale, (ii) selective amplifi-cation of bottom-up signals by feedback that utilizes spatial, temporal, or task-related context information, and (iii) automatic gain control via center-surround competitive interaction and activity normalization. We use these principles as a framework to design and develop bio-inspired models for form and motion processing. Our models replicate experimen-tal findings and, furthermore, provide a functional explanation for psy