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 June 2004 | Published
Book Section - Chapter Open

Is bottom-up attention useful for object recognition?


A key problem in learning 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 which is not associated to the objects. We investigate empirically to what extent pure bottom-up attention can extract useful information about the location, size and shape of objects from images and demonstrate how this information can be utilized to enable unsupervised learning of objects from unlabeled images. Our experiments demonstrate that the proposed approach to using bottom-up attention is indeed useful for a variety of applications.

Additional Information

© 2004 IEEE. Issue Date: 27 June-2 July 2004. Date of Current Version: 19 July 2004. This project was funded by the NSF Engineering Research Center for Neuromorphic Systems Engineering at Caltech, by an NSF-ITR award, the NIH and the Keck Foundation. The shape estimation code was developed by the authors as part of the "iNVT" community effort (http://ilab.usc.edu/toolkit). We would like to thank 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.

Attached Files

Published - RUTcvpr04.pdf


Files (758.1 kB)
Name Size Download all
758.1 kB Preview Download

Additional details

September 14, 2023
January 13, 2024