Unsupervised Object Segmentation with Explicit Localization Module
This work addresses the problem of segmenting objects without supervision for computer vision applications, presenting an incremental improvement over existing methods.
The paper tackles unsupervised object segmentation by introducing an explicit localization module that iteratively segments objects based on pixel-level reconstruction quality, showing improved segmentation quality, particularly on challenging backgrounds.
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.