Generating superpixels using deep image representations

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.

References in corpus (6)

• Semi-Supervised Classification with Graph Convolutional Networks
• ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• Superpixels: An Evaluation of the State-of-the-Art
• Scaling the Scattering Transform: Deep Hybrid Networks
• Efficient semantic image segmentation with superpixel pooling