MASON: A Model AgnoStic ObjectNess Framework

TL;DR

MASON is a versatile, model-agnostic deep learning framework that localizes foreground objects at pixel-level precision across diverse images without task-specific training.

Contribution

It introduces a simple, effective method for object localization that is category-independent and can be integrated with any existing network without additional training.

Findings

Works effectively across diverse image types

Achieves pixel-level object localization

Compatible with various neural network models

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.