Changes-Aware Transformer: Learning Generalized Changes Representation

TL;DR

This paper introduces a Changes-Aware Transformer that learns a generalized representation of changes in bi-temporal images, improving change detection accuracy and generalization across datasets.

Contribution

The paper proposes a novel Changes-Aware Transformer (CAT) that refines difference features using cosine cross-attention, enabling better change detection and compatibility with existing methods.

Findings

Achieves state-of-the-art performance on remote sensing and street scene datasets.

Effectively perceives changed and unchanged pixels in the difference feature space.

Demonstrates excellent generalization across different datasets.

Abstract

Difference features obtained by comparing the images of two periods play an indispensable role in the change detection (CD) task. However, a pair of bi-temporal images can exhibit diverse changes, which may cause various difference features. Identifying changed pixels with differ difference features to be the same category is thus a challenge for CD. Most nowadays' methods acquire distinctive difference features in implicit ways like enhancing image representation or supervision information. Nevertheless, informative image features only guarantee object semantics are modeled and can not guarantee that changed pixels have similar semantics in the difference feature space and are distinct from those unchanged ones. In this work, the generalized representation of various changes is learned straightforwardly in the difference feature space, and a novel Changes-Aware Transformer (CAT) for refining difference features is proposed. This generalized representation can perceive which pixels are changed and which are unchanged and further guide the update of pixels' difference features. CAT effectively accomplishes this refinement process through the stacked cosine cross-attention layer and self-attention layer. After refinement, the changed pixels in the difference feature space are closer to each other, which facilitates change detection. In addition, CAT is compatible with various backbone networks and existing CD methods. Experiments on remote sensing CD data set and street scene CD data set show that our method achieves state-of-the-art performance and has excellent generalization.