MASON: A Model AgnoStic ObjectNess Framework

K J Joseph, Rajiv Chunilal Patel, Amit Srivastava, Uma Gupta, Vineeth N Balasubramanian; Proceedings of the European Conference on Computer Vision (ECCV) Workshops, 2018, pp. 0-0


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 modelagnostic 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.

Related Material

author = {J Joseph, K and Chunilal Patel, Rajiv and Srivastava, Amit and Gupta, Uma and N Balasubramanian, Vineeth},
title = {MASON: A Model AgnoStic ObjectNess Framework},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV) Workshops},
month = {September},
year = {2018}