Box2Change: A Novel Weakly Supervised Way for Change Detection via Consistency Instance Segmentation

Fang Liu, Kanghua Yin, Jia Liu, Jingxiang Yang, Xu Tang, Liang Xiao

Abstract: Change detection in remote sensing images aims at revealing interesting changes about the Earth surface and has been one of the most important issues in Earth observation. In recent years, lots of fully supervised change detection methods have achieved good performance with the help of deep learning architectures, which rely on large amounts of pixel-level labels. However, obtaining high-quality pixel-level labels is laborious and expensive. To alleviate this problem, we propose a novel weakly supervised change detection way via consistency instance segmentation called Box2Change, which requires only box-level labels and achieves competitive results to a fully supervised change detection method. Compared with pixel-level label, it is much more efficient to get box-level label, which locates the potential changed area by a rectangle box. There are two key components in the proposed method: the changed instance segmentation (CIS) and the self-supervised consistency learning (SSCL) in affine space. The former generates multiscale changed instances, which learns positional information from box-level labels and segment the instance boundaries within a given bounded region. The latter introduces affine transform and employs consistency constraints in a self-supervised manner to increase the robustness to pseudo-change situations caused by light or noise. In experiments, three popular public change detection datasets are tested, and both visual and numerical assessments are discussed, where the proposed method exhibits competitive performance to fully supervised methods and achieves the state-of-the-art results compared with the other weakly supervised change detection methods.

External IDs:doi:10.1109/tgrs.2025.3589090