Where-What Network 5: Dealing with scales for objects in complex backgrounds

Abstract

The biologically-inspired developmental Where-What Networks (WWN) are general purpose visuomotor networks for detecting and recognizing objects from complex backgrounds, modeling the dorsal and ventral streams of the biological visual cortex. The networks are designed for the attention and recognition problem. The architecture in previous versions were meant for a single scale of foreground. This paper focuses on Where-What Network-5 (WWN-5), the extension for multiple scales. WWN-5 can learn three concepts of an object: type, location and scale.