Learning Semantic-Robust Change Detection via Semantic-Invariant Self-Distillation

2026-07-21

AI Summary

This work addresses the vulnerability of remote sensing change detection to non-semantic perturbations such as illumination and shadow variations, which often lead to false positives and degraded generalization. To mitigate this issue, the authors propose SCDistill, a novel framework featuring a semantics-invariant self-distillation mechanism. By leveraging diffusion models to synthesize paired data with realistic non-semantic disturbances, SCDistill jointly enhances semantic change discrimination through representation learning and data augmentation. The method achieves state-of-the-art performance across multiple remote sensing change detection benchmarks and demonstrates strong generalization capabilities in both binary change detection and change captioning tasks.

Abstract

Change detection aims to identify semantic changes between remote sensing images. However, features from models are easily disturbed by non-semantic variations, such as illumination, shadows, and atmospheric changes, leading to false alarms and limited generalization in real-world scenarios. In this paper, we propose \textbf{SCDistill}, a framework for learning semantic-robust change detection via semantic-invariant self-distillation. First, to strengthen semantic consistency, we introduce a semantic-invariant self-distillation strategy that learns semantic robustness from perturbed yet semantically consistent data, empowering the change detector to extract disturbance-resistant features and achieve more reliable and accurate semantic change identification. Second, to expand paired data with non-semantic variations, we design a diffusion-based perturbation simulation pipeline that synthesizes complex environmental changes, enabling the model to explicitly learn to distinguish semantic changes from appearance-level fluctuations and reduce false alarms caused by non-semantic disturbances. These components promote robustness from data and representation perspectives, leading to synergistic performance gains. Extensive experiments demonstrate that SCDistill achieves state-of-the-art performance on multiple semantic change detection benchmarks and exhibits strong generalization to binary change detection and change captioning tasks. Code is accessible at https://github.com/elecreak/SCDistill.

Problem

• change detection
• semantic robustness
• non-semantic variations
• remote sensing
• false alarms

Innovation

• semantic-invariant self-distillation
• change detection
• diffusion-based perturbation simulation
• semantic robustness
• remote sensing