MASON: A Model AgnoStic ObjectNess Framework

Balasubramanian, Vineeth N and Chunilal Patel, Rajiv and Srivastava, Amit and et al, . (2019) MASON: A Model AgnoStic ObjectNess Framework. In: 15th European Conference on Computer Vision, ECCV, 8-14 September 2018, Germany.

Full text not available from this repository. (Request a copy)

Abstract

This paper proposes a simple, yet very effective method to localize dominant foreground objects in an image, to pixel-level precision. The proposed method ‘MASON’ (Model-AgnoStic ObjectNess) uses a deep convolutional network to generate category-independent and model-agnostic heat maps for any image. The network is not explicitly trained for the task, and hence, can be used off-the-shelf in tandem with any other network or task. We show that this framework scales to a wide variety of images, and illustrate the effectiveness of MASON in three varied application contexts.

[error in script]

IITH Creators:	IITH Creators ORCiD Balasubramanian, Vineeth N UNSPECIFIED
Item Type:	Conference or Workshop Item (Paper)
Subjects:	Computer science
Divisions:	Department of Computer Science & Engineering
Depositing User:	Library Staff
Date Deposited:	28 Oct 2019 11:28
Last Modified:	28 Oct 2019 11:28
URI:	http://raiithold.iith.ac.in/id/eprint/6805
Publisher URL:	http://doi.org/10.1007/978-3-030-11021-5_40
Related URLs:	Google Scholar

Actions (login required)

View Item

Statistics for this ePrint Item