MASON: A Model AgnoStic ObjectNess Framework
This provides a general-purpose tool for object localization that can be integrated with any network or task, though it appears incremental as it builds on existing deep convolutional methods.
The paper tackles the problem of localizing dominant foreground objects in images with pixel-level precision, proposing MASON, a model-agnostic framework that generates category-independent heat maps without explicit training, and demonstrates its effectiveness across varied applications.
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.