HyRet-Change: A hybrid retentive network for remote sensing change detection

2025-06-15

AI Summary

Remote sensing change detection faces three key challenges: severe false-change interference, difficulty in detecting subtle changes, and high computational complexity of Transformer-based self-attention mechanisms, which hinder effective local-detail modeling. To address these, this paper proposes a Siamese-style Hybrid Retention Network (HRNet). Its core contributions are: (1) a novel parallel Convolution–Retention module that jointly captures local texture patterns and long-range dependencies by computing feature differences; and (2) an adaptive local–global interactive context-aware mechanism enabling cross-scale feature mutual learning and discriminative enhancement. Extensive experiments on three benchmark datasets—LEVIR-CD, WHU-CD, and CDD—demonstrate state-of-the-art performance, with significant suppression of false changes and improved detection accuracy for fine-grained changes. The source code is publicly available.

Technology Category

• Computer Vision: Image and Video Retrieval
• Machine Learning: Multi-instance/Multi-view Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Large-scale security measurements
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

Abstract

Recently convolution and transformer-based change detection (CD) methods provide promising performance. However, it remains unclear how the local and global dependencies interact to effectively alleviate the pseudo changes. Moreover, directly utilizing standard self-attention presents intrinsic limitations including governing global feature representations limit to capture subtle changes, quadratic complexity, and restricted training parallelism. To address these limitations, we propose a Siamese-based framework, called HyRet-Change, which can seamlessly integrate the merits of convolution and retention mechanisms at multi-scale features to preserve critical information and enhance adaptability in complex scenes. Specifically, we introduce a novel feature difference module to exploit both convolutions and multi-head retention mechanisms in a parallel manner to capture complementary information. Furthermore, we propose an adaptive local-global interactive context awareness mechanism that enables mutual learning and enhances discrimination capability through information exchange. We perform experiments on three challenging CD datasets and achieve state-of-the-art performance compared to existing methods. Our source code is publicly available at https://github.com/mustansarfiaz/HyRect-Change.

Problem

• Interacting local and global dependencies to reduce pseudo changes
• Overcoming limitations of standard self-attention in change detection
• Integrating convolution and retention for multi-scale feature adaptability

Innovation

• Hybrid convolution and retention mechanisms
• Parallel feature difference module
• Adaptive local-global interaction mechanism