NeXt2Former-CD: Efficient Remote Sensing Change Detection with Modern Vision Architectures

2026-02-20

AI Summary

This work addresses performance degradation in remote sensing change detection caused by registration residuals, small-object misalignment, and semantic ambiguity. To this end, the authors propose an end-to-end framework that, for the first time, integrates a ConvNeXt encoder pretrained with DINOv3, a deformable attention-based temporal fusion module, and a Mask2Former decoder to achieve robust spatiotemporal feature alignment and fine-grained change segmentation. The method consistently outperforms existing approaches in terms of F1 score and IoU on the LEVIR-CD, WHU-CD, and CDD benchmarks, while maintaining inference latency comparable to state-space models. Notably, it demonstrates significantly enhanced robustness to registration errors and improved sensitivity to small-scale changes, establishing a new paradigm for high-resolution remote sensing change detection.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• 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: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

State Space Models (SSMs) have recently gained traction in remote sensing change detection (CD) for their favorable scaling properties. In this paper, we explore the potential of modern convolutional and attention-based architectures as a competitive alternative. We propose NeXt2Former-CD, an end-to-end framework that integrates a Siamese ConvNeXt encoder initialized with DINOv3 weights, a deformable attention-based temporal fusion module, and a Mask2Former decoder. This design is intended to better tolerate residual co-registration noise and small object-level spatial shifts, as well as semantic ambiguity in bi-temporal imagery. Experiments on LEVIR-CD, WHU-CD, and CDD datasets show that our method achieves the best results among the evaluated methods, improving over recent Mamba-based baselines in both F1 score and IoU. Furthermore, despite a larger parameter count, our model maintains inference latency comparable to SSM-based approaches, suggesting it is practical for high-resolution change detection tasks.

Problem

• change detection
• remote sensing
• co-registration noise
• spatial shift
• semantic ambiguity

Innovation

• ConvNeXt
• Deformable Attention
• Mask2Former
• Change Detection
• Remote Sensing