Combining Multi-level Contexts of Superpixel using Convolutional Neural Networks to perform Natural Scene Labeling

TL;DR

This paper introduces a superpixel-based semantic segmentation method that leverages multi-level contextual information and ensemble techniques, outperforming existing approaches in natural scene labeling tasks.

Contribution

It proposes a novel multi-level superpixel context integration combined with ensemble methods and uncertainty analysis for improved scene labeling accuracy.

Findings

Outperforms modern segmentation approaches on the same dataset

Utilizes ensemble methods like max-voting and weighted-average

Employs Dempster-Shafer theory for class confusion analysis

Abstract

Modern deep learning algorithms have triggered various image segmentation approaches. However most of them deal with pixel based segmentation. However, superpixels provide a certain degree of contextual information while reducing computation cost. In our approach, we have performed superpixel level semantic segmentation considering 3 various levels as neighbours for semantic contexts. Furthermore, we have enlisted a number of ensemble approaches like max-voting and weighted-average. We have also used the Dempster-Shafer theory of uncertainty to analyze confusion among various classes. Our method has proved to be superior to a number of different modern approaches on the same dataset.