EoCD: Encoder only Remote Sensing Change Detection

2026-02-05

AI Summary

This work proposes a lightweight, encoder-only framework for remote sensing change detection, addressing the redundancy and high computational cost of existing methods that rely on dual-temporal Siamese encoders or complex decoders. By fusing bi-temporal inputs at an early stage and replacing conventional decoders with a parameter-free multi-scale feature fusion module, the proposed architecture achieves significant structural simplification. The study demonstrates that change detection performance is predominantly governed by the encoder, and the method attains an optimal balance of high accuracy, low model complexity, and fast inference across four challenging benchmark datasets. Furthermore, the framework exhibits strong compatibility with diverse encoder architectures, underscoring its versatility and efficiency.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Deep Generative Models & Autoencoders
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Being a cornerstone of temporal analysis, change detection has been playing a pivotal role in modern earth observation. Existing change detection methods rely on the Siamese encoder to individually extract temporal features followed by temporal fusion. Subsequently, these methods design sophisticated decoders to improve the change detection performance without taking into consideration the complexity of the model. These aforementioned issues intensify the overall computational cost as well as the network's complexity which is undesirable. Alternatively, few methods utilize the early fusion scheme to combine the temporal images. These methods prevent the extra overhead of Siamese encoder, however, they also rely on sophisticated decoders for better performance. In addition, these methods demonstrate inferior performance as compared to late fusion based methods. To bridge these gaps, we introduce encoder only change detection (EoCD) that is a simple and effective method for the change detection task. The proposed method performs the early fusion of the temporal data and replaces the decoder with a parameter-free multiscale feature fusion module thereby significantly reducing the overall complexity of the model. EoCD demonstrate the optimal balance between the change detection performance and the prediction speed across a variety of encoder architectures. Additionally, EoCD demonstrate that the performance of the model is predominantly dependent on the encoder network, making the decoder an additional component. Extensive experimentation on four challenging change detection datasets reveals the effectiveness of the proposed method.

Problem

• change detection
• remote sensing
• model complexity
• computational cost
• temporal fusion

Innovation

• Encoder-only
• Change Detection
• Early Fusion
• Parameter-free Fusion
• Remote Sensing