A Dual-Branch Framework for Semantic Change Detection with Boundary and Temporal Awareness

2026-02-12

AI Summary

This work proposes DBTANet, a dual-branch network designed to address boundary ambiguity and insufficient temporal modeling in semantic change detection for remote sensing imagery. The architecture integrates global semantics and boundary priors from a frozen SAM branch with local spatial details extracted by a ResNet34 branch. To enhance temporal coherence and boundary delineation, the method introduces two novel components: a Bidirectional Temporal Awareness Module (BTAM) and a Temporal Gaussian Smoothing Projection Module (GSPM). These innovations enable precise, temporally consistent segmentation of change regions. Evaluated on two public remote sensing change detection benchmarks, DBTANet achieves state-of-the-art performance, significantly improving both boundary accuracy and semantic class discrimination.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Knowledge Representation and Reasoning: Action, Change, and Causality
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Semantic Change Detection (SCD) aims to detect and categorize land-cover changes from bi-temporal remote sensing images. Existing methods often suffer from blurred boundaries and inadequate temporal modeling, limiting segmentation accuracy. To address these issues, we propose a Dual-Branch Framework for Semantic Change Detection with Boundary and Temporal Awareness, termed DBTANet. Specifically, we utilize a dual-branch Siamese encoder where a frozen SAM branch captures global semantic context and boundary priors, while a ResNet34 branch provides local spatial details, ensuring complementary feature representations. On this basis, we design a Bidirectional Temporal Awareness Module (BTAM) to aggregate multi-scale features and capture temporal dependencies in a symmetric manner. Furthermore, a Gaussian-smoothed Projection Module (GSPM) refines shallow SAM features, suppressing noise while enhancing edge information for boundary-aware constraints. Extensive experiments on two public benchmarks demonstrate that DBTANet effectively integrates global semantics, local details, temporal reasoning, and boundary awareness, achieving state-of-the-art performance.

Problem

• Semantic Change Detection
• Boundary Awareness
• Temporal Modeling
• Remote Sensing
• Bi-temporal Images

Innovation

• Dual-Branch Framework
• Boundary Awareness
• Temporal Awareness
• Semantic Change Detection
• SAM Integration