Unsupervised Object Segmentation with Explicit Localization Module

11/21/2019
by   Weitang Liu, et al.
12

In this paper, we propose a novel architecture that iteratively discovers and segments out the objects of a scene based on the image reconstruction quality. Different from other approaches, our model uses an explicit localization module that localizes objects of the scene based on the pixel-level reconstruction qualities at each iteration, where simpler objects tend to be reconstructed better at earlier iterations and thus are segmented out first. We show that our localization module improves the quality of the segmentation, especially on a challenging background.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset