Speeding up top-down attention control learning by using full observation knowledge

We present a general mathematical description of the top-down attention control problem. Three important components are identified in the model: context extraction, attention focus and decision making. The context gives a coarse blurry representation of the whole input; the attention module models the focus of attention on a limited part of input, and the decision making component accounts the final decision of the agent for its motory actions. In order to achieve a faster convergence of attention learning in the online phase, an offline optimization step is performed in advance. To do so, we incorporate the knowledge of a full observer agent that has approximately learned the optimal decision making of the task. The simulation results show that by employing our algorithm, the learning speed is improved.

[1]  Antonio Torralba,et al.  Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope , 2001, International Journal of Computer Vision.

[2]  Antonio Torralba,et al.  Building the gist of a scene: the role of global image features in recognition. , 2006, Progress in brain research.

[3]  Michael I. Jordan,et al.  Reinforcement Learning Algorithm for Partially Observable Markov Decision Problems , 1994, NIPS.

[4]  Antonio Torralba,et al.  Contextual guidance of eye movements and attention in real-world scenes: the role of global features in object search. , 2006, Psychological review.

[5]  Hossein Mobahi,et al.  Concept Oriented Imitation Towards Verbal Human-Robot Interaction , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[6]  Antonio Torralba,et al.  Using the Forest to See the Trees: A Graphical Model Relating Features, Objects, and Scenes , 2003, NIPS.

[7]  Majid Nili Ahmadabadi,et al.  A Probabilistic Reinforcement-Based Approach to Conceptualization , 2008 .

[8]  Majid Nili Ahmadabadi,et al.  Comparing Learning Attention Control in Perceptual and Decision Space , 2009, WAPCV.

[9]  Jean Underwood,et al.  Visual attention while driving: sequences of eye fixations made by experienced and novice drivers , 2003, Ergonomics.

[10]  Guillaume A. Rousselet,et al.  Processing scene context: Fast categorization and object interference , 2007, Vision Research.

[11]  Majid Nili Ahmadabadi,et al.  Optimal Local Basis: A Reinforcement Learning Approach for Face Recognition , 2009, International Journal of Computer Vision.

[12]  A. L. Yarbus Eye Movements During Perception of Complex Objects , 1967 .

[13]  Deniz Erdogmus,et al.  Information Theoretic Learning , 2005, Encyclopedia of Artificial Intelligence.

[14]  Laurent Itti,et al.  Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Rapid Biologically-inspired Scene Classification Using Features Shared with Visual Attention , 2022 .