Be the Change You Want to See: Revisiting Remote Sensing Change Detection Practices

TL;DR

This paper emphasizes the importance of fundamental design choices in remote sensing change detection, showing that well-optimized simple models can outperform complex architectures on multiple datasets.

Contribution

It systematically analyzes core design choices in change detection models and demonstrates their significant impact on performance, challenging the focus on architectural complexity.

Findings

Well-optimized simple models can match or outperform complex architectures.

Fundamental design choices have a greater impact than architectural additions.

Guidelines improve performance across various change detection methods.

Abstract

Remote sensing change detection aims to localize semantic changes between images of the same location captured at different times. In the past few years, newer methods have attributed enhanced performance to the additions of new and complex components to existing architectures. Most fail to measure the performance contribution of fundamental design choices such as backbone selection, pre-training strategies, and training configurations. We claim that such fundamental design choices often improve performance even more significantly than the addition of new architectural components. Due to that, we systematically revisit the design space of change detection models and analyse the full potential of a well-optimised baseline. We identify a set of fundamental design choices that benefit both new and existing architectures. Leveraging this insight, we demonstrate that when carefully designed, even an architecturally simple model can match or surpass state-of-the-art performance on six challenging change detection datasets. Our best practices generalise beyond our architecture and also offer performance improvements when applied to related methods, indicating that the space of fundamental design choices has been underexplored. Our guidelines and architecture provide a strong foundation for future methods, emphasizing that optimizing core components is just as important as architectural novelty in advancing change detection performance. Code: https://github.com/blaz-r/BTC-change-detection