Data-Driven Objectness

January 2015

Data-Driven Objectness

Authors:

Hongwen Kang, Martial Hebert, Alexei A. Efros, and Takeo Kanade

Abstract:

We propose a data-driven approach to estimate the likelihood that an image segment corresponds to a scene object (its “objectness”) by comparing it to a large collection of example object regions. We demonstrate that when the application domain is known, for example, in our case activity of daily living (ADL), we can capture the regularity of the domain specific objects using millions of exemplar object regions. Our approach to estimating the objectness of an image region proceeds in two steps: 1) finding the exemplar regions that are the most similar to the input image segment; 2) calculating the objectness of the image segment by combining segment properties, mutual consistency across the nearest exemplar regions, and the prior probability of each exemplar region. In previous work, parametric objectness models were built from a small number of manually annotated objects regions, instead, our data-driven approach uses 5 million object regions along with their metadata information. Results on multiple data sets demonstrates our data-driven approach compared to the existing model based techniques. We also show the application of our approach in improving the performance of object discovery algorithms.
@article{Kang-2015-122982,
author = {Hongwen Kang And Martial Hebert And Alexei A. Efros And Takeo Kanade},
title = {Data-Driven Objectness},
journal = {Proceedings of IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2015},
month = {January},
volume = {37},
number = {1},
pages = {189 - 195},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.