Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published October 2005 | public
Journal Article

Selective visual attention enables learning and recognition of multiple objects in cluttered scenes

Abstract

A key problem in learning representations of multiple objects from unlabeled images is that it is a priori impossible to tell which part of the image corresponds to each individual object, and which part is irrelevant clutter. Distinguishing individual objects in a scene would allow unsupervised learning of multiple objects from unlabeled images. There is psychophysical and neurophysiological evidence that the brain employs visual attention to select relevant parts of the image and to serialize the perception of individual objects. We propose a method for the selection of salient regions likely to contain objects, based on bottom-up visual attention. By comparing the performance of David Lowe's recognition algorithm with and without attention, we demonstrate in our experiments that the proposed approach can enable one-shot learning of multiple objects from complex scenes, and that it can strongly improve learning and recognition performance in the presence of large amounts of clutter.

Additional Information

Received 19 December 2003; accepted 29 September 2004. Available online 15 June 2005. This project was funded by the NSF Engineering Research Center for Neuromorphic Systems Engineering at Caltech, by an NSF-ITR award, the NIH, the NIMH, the Keck Foundation, and a Sloan-Swartz Fellowship to U.R. The region selection code was developed by the authors as part of the "iNVT" community effort (http://ilab.usc.edu/toolkit). We thank Laurent Itti and the anonymous reviewers for comments on previous versions of the manuscript, and Evolution Robotics for making their robotic vision software development kit available to us. High-resolution background images were provided by TNO Human Factors Research Institute, the Netherlands.

Additional details

Created:
September 15, 2023
Modified:
October 23, 2023