Dynamic Relevance: Vision-Based Focus of Attention Using Artificial Neural Networks. (Technical Note)

Abstract This paper presents a method for ascertaining the relevance of inputs in vision-based tasks by exploiting temporal coherence and predictability. In contrast to the tasks explored in many previous relevance experiments, the class of tasks examined in this study is one in which relevance is a time-varying function of the previous and current inputs. The method proposed in this paper dynamically allocates relevance to inputs by using expectations of their future values. As a model of the task is learned, the model is simultaneously extended to create task-specific predictions of the future values of inputs. Inputs that are not relevant, and therefore not accounted for in the model, will not be predicted accurately. These inputs can be de-emphasized, and, in turn, a new, improved, model of the task created. The techniques presented in this paper have been successfully applied to the vision-based autonomous control of a land vehicle, vision-based hand tracking in cluttered scenes, and the detection of faults in the plasma-etch step of semiconductor wafers.

[1]  Rich Caruana,et al.  Greedy Attribute Selection , 1994, ICML.

[2]  L. S. Davis,et al.  The Use Of A Radial Basis Function Network For Visual Autonomous Road Following , 1993, Proceedings of the Intelligent Vehicles '93 Symposium.

[3]  M. Kramer.  Nonlinear principal component analysis using autoassociative neural networks , 1991 .

[4]  Kurt Hornik,et al.  Neural networks and principal component analysis: Learning from examples without local minima , 1989, Neural Networks.

[5]  Dean A. Pomerleau,et al.  Neural Network Perception for Mobile Robot Guidance , 1993 .

[6]  Dean Pomerleau,et al.  Efficient Training of Artificial Neural Networks for Autonomous Navigation , 1991, Neural Computation.

[7]  Dean Pomerleau,et al.  Reliability estimation for neural network based autonomous driving , 1994, Robotics Auton. Syst..

[8]  Ron Kohavi,et al.  Irrelevant Features and the Subset Selection Problem , 1994, ICML.

[9]  Shumeet Baluja,et al.  Expectation-based selective attention for visual monitoring and control of a robot vehicle , 1997, Robotics Auton. Syst..

[10]  Christof Koch,et al.  Selecting One Among the Many: A Simple Network Implementing Shifts in Selective Visual Attention , 1984 .

[11]  Shumeet Baluja,et al.  Expectation-based selective attention , 1996 .

[12]  Takeo Kanade,et al.  Neural Network-Based Face Detection , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Ernst D. Dickmanns,et al.  Expectation-based dynamic scene understanding , 1993 .

[14]  Kah Kay Sung,et al.  Learning and example selection for object and pattern detection , 1995 .

[15]  Thomas G. Dietterich,et al.  Learning with Many Irrelevant Features , 1991, AAAI.

[16]  Shumeet Baluja,et al.  Using a Saliency Map for Active Spatial Selective Attention: Implementation & Initial Results , 1994, NIPS.

[17]  Stuart J. Russell,et al.  Object Identification in a Bayesian Context , 1997, IJCAI.