papers AI Learner
The Github is limit! Click to go to the new site.

Generating superpixels using deep image representations

2019-03-11
Thomas Verelst, Matthew Blaschko, Maxim Berman

Abstract

Superpixel algorithms are a common pre-processing step for computer vision algorithms such as segmentation, object tracking and localization. Many superpixel methods only rely on colors features for segmentation, limiting performance in low-contrast regions and applicability to infrared or medical images where object boundaries have wide appearance variability. We study the inclusion of deep image features in the SLIC superpixel algorithm to exploit higher-level image representations. In addition, we devise a trainable superpixel algorithm, yielding an intermediate domain-specific image representation that can be applied to different tasks. A clustering-based superpixel algorithm is transformed into a pixel-wise classification task and superpixel training data is derived from semantic segmentation datasets. Our results demonstrate that this approach is able to improve superpixel quality consistently.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1903.04586

PDF

http://arxiv.org/pdf/1903.04586


Similar Posts

Comments