Learning by integrating information within and across fixations

Authors:
Predrag Neskovic;Liang Wu;Leon N Cooper
Affiliations:
Institute for Brain and Neural Systems and Department of Physics, Brown University, Providence, RI;Institute for Brain and Neural Systems and Department of Physics, Brown University, Providence, RI;Institute for Brain and Neural Systems and Department of Physics, Brown University, Providence, RI
Venue:
ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part II
Year:
2006

Citing 6
Cited 2

SEEMORE: combining color, shape, and texture histogramming in a neurally inspired approach to visual object recognition

Neural Computation
Object Recognition from Local Scale-Invariant Features

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
A Bayesian Approach to Unsupervised One-Shot Learning of Object Categories

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Learning to Detect Objects in Images via a Sparse, Part-Based Representation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Object Recognition with Features Inspired by Visual Cortex

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Sharing features: efficient boosting procedures for multiclass object detection

CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition

Learning faces with the BIAS model: On the importance of the sizes and locations of fixation regions

Neurocomputing
Biologically inspired bayes learning and its dependence on the distribution of the receptive fields

ICNC'06 Proceedings of the Second international conference on Advances in Natural Computation - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this work we introduce a Bayesian Integrate And Shift (BIAS) model for learning object categories. The model is biologically inspired and uses Bayesian inference to integrate information within and across fixations. In our model, an object is represented as a collection of features arranged at specific locations with respect to the location of the fixation point. Even though the number of feature detectors that we use is large, we show that learning does not require a large amount of training data due to the fact that between an object and features we introduce an intermediate representation, object views, and thus reduce the dependence among the feature detectors. We tested the system on four object categories and demonstrated that it can learn a new category from only a few training examples.