Abstract
An Integrated System for Incremental Learning of Multiple Visual Categories
Highlights
An amazing capability of the human visual system is the ability to learn an enormous repertoire of visual categories
This hypothesis generation is repeated until the user confirms or corrects the categorization decisions of the long term memory (LTM) representation, which triggers the collection of new training vectors into the short term memory (STM)
The incremental learning of the LTM representation is performed in both states and is even continued, if currently no new object views are presented, because this knowledge transfer typically takes much longer than the STM training
Summary
An amazing capability of the human visual system is the ability to learn an enormous repertoire of visual categories. Since several years many architectures dealing with object detection and categorization tasks have been proposed in the computer vision community Most of these approaches are only based on local parts-based features, which are extracted around some defined interest points (e.g. implicit shape models (ISM) [8]) to build up object models for categories like faces or cars. The advantages of such models are their robustness against partial occlusion and scale changes, and the ability to deal with clutter.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
