Online learning of task-driven object-based visual attention control
Image and Vision Computing
A biologically-motivated computational model for learning task-driven and objectbased visual attention control in interactive environments is proposed. Our model consists of three layers. First, in the early visual processing layer, most salient location of a scene is derived using the biased saliency-based bottom-up model of visual attention. Then a cognitive component in the higher visual processing layer performs an application specific operation like object recognition at the focus of
... ion. From this information, a state is derived in the decision making and learning layer. Top-down attention is learned by the U-TREE algorithm which successively grows an object-based binary tree. Internal nodes in this tree check the existence of a certain object in the scene by biasing the early vision and the object recognition parts. Its leaves point to states in the action value table. Motor actions are associated with the leaves. After performing a motor action, the agent receives a reinforcement signal from the critic. This signal is alternately used for modifying the tree or updating the action selection policy. The proposed model is evaluated on visual navigation tasks, where obtained results lend support to the applicability and usefulness of the developed method for robotics. Abstract Fig. 7 . Learned attention tree for the map of Fig. 6 with pruning. Forty four states were clustered into 7 leaves. 100% correct policy was achieved.