Abstract
This work provides a framework for learning sequential attention in real-world visual object recognition, using an architecture of three processing stages. The first stage rejects irrelevant local descriptors based on an information theoretic saliency measure, providing candidates for foci of interest (FOI). The second stage investigates the information in the FOI using a codebook matcher and providing weak object hypotheses. The third stage integrates local information via shifts of attention, resulting in chains of descriptor-action pairs that characterize object discrimination. A Q-learner adapts then from explorative search and evaluative feedback from entropy decreases on the attention sequences, eventually prioritizing shifts that lead to a geometry of descriptor-action scanpaths that is highly discriminative with respect to object recognition. The methodology is successfully evaluated on indoors (COIL-20 database) and outdoors (TSG-20 database) imagery, demonstrating significant impact by learning, outperforming standard local descriptor based methods both in recognition accuracy and processing time.
Original language | English |
---|---|
Title of host publication | ICML '05 |
Subtitle of host publication | Proceedings of the 22nd International Conference on Machine Learning |
Place of Publication | New York, NY, USA |
Publisher | ACM Press |
Pages | 649-656 |
Number of pages | 8 |
ISBN (Print) | 1-59593-180-5 |
DOIs | |
Publication status | Published - 2005 |
Externally published | Yes |
Event | 22nd International Conference on Machine learning, ICML 2005 - Bonn, Germany Duration: 7 Aug 2005 → 11 Aug 2005 Conference number: 22 |
Conference
Conference | 22nd International Conference on Machine learning, ICML 2005 |
---|---|
Abbreviated title | ICML |
Country/Territory | Germany |
City | Bonn |
Period | 7/08/05 → 11/08/05 |