Dense Fusion Classmate Network for Land Cover Classification

TL;DR

This paper introduces DFCNet, a dense fusion network designed to improve land cover classification in satellite images by effectively capturing mid-level structural information for more accurate pixel-level segmentation.

Contribution

The paper proposes a novel Dense Fusion Classmate Network that enhances land cover classification by integrating dense feature fusion to address the lack of mid-level structural information.

Findings

Improved segmentation accuracy on satellite land cover datasets

Effective capture of mid-level structural features

Enhanced pixel-level classification performance

Abstract

Recently, FCNs based methods have made great progress in semantic segmentation. Different with ordinary scenes, satellite image owns specific characteristics, which elements always extend to large scope and no regular or clear boundaries. Therefore, effective mid-level structure information extremely missing, precise pixel-level classification becomes tough issues. In this paper, a Dense Fusion Classmate Network (DFCNet) is proposed to adopt in land cover classification.