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 November 2011 | public
Book Section - Chapter

Multiclass Recognition and Part Localization with Humans in the Loop

Abstract

We propose a visual recognition system that is designed for fine-grained visual categorization. The system is composed of a machine and a human user. The user, who is unable to carry out the recognition task by himself, is interactively asked to provide two heterogeneous forms of information: clicking on object parts and answering binary questions. The machine intelligently selects the most informative question to pose to the user in order to identify the object's class as quickly as possible. By leveraging computer vision and analyzing the user responses, the overall amount of human effort required, measured in seconds, is minimized. We demonstrate promising results on a challenging dataset of uncropped images, achieving a significant average reduction in human effort over previous methods.

Additional Information

© 2011 IEEE. The authors thank Boris Babenko, Ryan Farrell, Kristen Grauman, and Peter Welinder for helpful discussions and feedback, as well as Jitendra Malik for suggesting time-to-decision as a relevant performance metric. Funding for this work was provided by the NSF GRFP for CW under Grant DGE 0707423, NSF Grant AGS-0941760, ONR MURI Grant N00014–08-1–0638, ONR MURI Grant N00014–06-1–0734, and ONR MURI Grant 1015 G NA127.

Additional details

Created:
August 19, 2023
Modified:
October 18, 2023