A Late-Stage Bitemporal Feature Fusion Network for Semantic Change Detection

TL;DR

This paper introduces a late-stage bitemporal feature fusion network with attention modules for improved semantic change detection in earth observation, achieving state-of-the-art results.

Contribution

It proposes a novel late-stage feature fusion approach with attention modules, addressing entanglement and refinement issues in previous models.

Findings

Achieves new state-of-the-art performance on SECOND and Landsat-SCD datasets.

Effective local-global attention modules enhance feature fusion and semantic highlighting.

Demonstrates superior accuracy over existing multi-task learning methods.

Abstract

Semantic change detection is an important task in geoscience and earth observation. By producing a semantic change map for each temporal phase, both the land use land cover categories and change information can be interpreted. Recently some multi-task learning based semantic change detection methods have been proposed to decompose the task into semantic segmentation and binary change detection subtasks. However, previous works comprise triple branches in an entangled manner, which may not be optimal and hard to adopt foundation models. Besides, lacking explicit refinement of bitemporal features during fusion may cause low accuracy. In this letter, we propose a novel late-stage bitemporal feature fusion network to address the issue. Specifically, we propose local global attentional aggregation module to strengthen feature fusion, and propose local global context enhancement module to highlight pivotal semantics. Comprehensive experiments are conducted on two public datasets, including SECOND and Landsat-SCD. Quantitative and qualitative results show that our proposed model achieves new state-of-the-art performance on both datasets.