Aug. 24, 2007 to Aug. 27, 2007
Predrag Neskovic , Brown University, USA
Ian Sherman , Brown University, USA
Liang Wu , Brown University, USA
Leon N Cooper , Brown University, USA
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICNC.2007.417
In this work we consider the Bayesian Integrate And Shift (BIAS) model for learning object categories and investigate its sensitivity to changes in the sizes and locations of fixation regions. We test the model using a face category and show that the learning algorithm is robust to large variations of the regions? sizes and locations. Specifically, we show that the performance is inversely proportional to the sizes of the fixation regions and that the preferred locations are those that are closer to the center of the object.
Predrag Neskovic, Ian Sherman, Liang Wu, Leon N Cooper, "How Important are the Sizes and Locations of Fixation Regions for the BIAS Model?", ICNC, 2007, 2007 3rd International Conference on Natural Computation, 2007 3rd International Conference on Natural Computation 2007, pp. 17-21, doi:10.1109/ICNC.2007.417