Generating superpixels using deep image representations
This addresses limitations in superpixel algorithms for computer vision tasks like segmentation, particularly in low-contrast or specialized domains such as infrared or medical images, though it is incremental.
The paper tackled the problem of superpixel generation by incorporating deep image features into the SLIC algorithm and developing a trainable method, resulting in consistent improvements in superpixel quality.
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.