Q-learning of sequential attention for visual object recognition from informative local descriptors

Lucas Paletta, Gerald Fritz, Christin Seifert

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

45 Citations (Scopus)


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 languageEnglish
Title of host publicationICML '05
Subtitle of host publicationProceedings of the 22nd International Conference on Machine Learning
Place of PublicationNew York, NY, USA
PublisherACM Press
Number of pages8
ISBN (Print)1-59593-180-5
Publication statusPublished - 2005
Externally publishedYes
Event22nd International Conference on Machine learning, ICML 2005 - Bonn, Germany
Duration: 7 Aug 200511 Aug 2005
Conference number: 22


Conference22nd International Conference on Machine learning, ICML 2005
Abbreviated titleICML


Dive into the research topics of 'Q-learning of sequential attention for visual object recognition from informative local descriptors'. Together they form a unique fingerprint.

Cite this