WWN-2: A biologically inspired neural network for concurrent visual attention and recognition

Zhengping Ji, Juyang Weng
2010 The 2010 International Joint Conference on Neural Networks (IJCNN)  
Attention and recognition have been addressed separately as two challenging computational vision problems, but an engineering-grade solution to their integration and interaction is still open. Inspired by the brain's dorsal and ventral pathways in cortical visual processing, we present a neuromorphic architecture, called Where-What Network 2 (WWN-2), to integrate object attention and recognition interactively through their experience-based development. This architecture enables three types of
more » ... tention: feature-based bottom-up attention, position-based top-down attention, and object-based top-down attention, as three possible information flows through the Yshaped network. The learning mechanism of the network is rooted in a simple but efficient cell-centered synaptic update model, entailing the dual optimization of Hebbian directions and cell firing-age dependent step sizes. The inputs to the network are a sequence of images, where specific foreground objects may appear anywhere within an unknown, complex, natural background. The WWN-2 regulates the network to dynamically establish and consolidate position-specified and type-specified representations through a supervised learning mode. The network has reached 92.5% object recognition rate and an average of 1.5 pixels in position error after 20 epochs of training.
doi:10.1109/ijcnn.2010.5596778 dblp:conf/ijcnn/JiW10 fatcat:3jtvzt6d45acraiawxc6fvl2ta