Papers › SChanger: Change Detection from a Semantic Change and Spatial Consistency Perspective

SChanger: Change Detection from a Semantic Change and Spatial Consistency Perspective

26 Mar 2025arXiv:2503.20734archive 2025-07-28

Ziyu Zhou, Keyan Hu, Yutian Fang, Xiaoping Rui

Change detection is a key task in Earth observation applications. Recently, deep learning methods have demonstrated strong performance and widespread application. However, change detection faces data scarcity due to the labor-intensive process of accurately aligning remote sensing images of the same area, which limits the performance of deep learning algorithms. To address the data scarcity issue, we develop a fine-tuning strategy called the Semantic Change Network (SCN). We initially pre-train the model on single-temporal supervised tasks to acquire prior knowledge of instance feature extraction. The model then employs a shared-weight Siamese architecture and extended Temporal Fusion Module (TFM) to preserve this prior knowledge and is fine-tuned on change detection tasks. The learned semantics for identifying all instances is changed to focus on identifying only the changes. Meanwhile, we observe that the locations of changes between the two images are spatially identical, a concept we refer to as spatial consistency. We introduce this inductive bias through an attention map that is generated by large-kernel convolutions and applied to the features from both time points. This enhances the modeling of multi-scale changes and helps capture underlying relationships in change detection semantics. We develop a binary change detection model utilizing these two strategies. The model is validated against state-of-the-art methods on six datasets, surpassing all benchmark methods and achieving F1 scores of 92.87%, 86.43%, 68.95%, 97.62%, 84.58%, and 93.20% on the LEVIR-CD, LEVIR-CD+, S2Looking, CDD, SYSU-CD, and WHU-CD datasets, respectively.

PaperPDFCode

Code

zhouziyu-cn/SChanger officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Change Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Change Detection CDD Dataset (season-varying) SChanger-base F1-Score 97.62 #7 of 18 Archive leaderboard report
Change Detection CDD Dataset (season-varying) SChanger-small F1-Score 95.75 #11 of 18 Archive leaderboard report
Change Detection LEVIR+ SChanger-base F1 86.43 #2 of 9 Archive leaderboard report
Change Detection LEVIR+ SChanger-small F1 86.20 #3 of 9 Archive leaderboard report
Change Detection LEVIR-CD SChanger-base F1 92.87 #1 of 28 Archive leaderboard report
Change Detection LEVIR-CD SChanger-small F1 92.45 #4 of 28 Archive leaderboard report
Change Detection S2Looking SChanger-base F1-Score 68.95 #1 of 11 Archive leaderboard report
Change Detection S2Looking SChanger-small F1-Score 68.20 #2 of 11 Archive leaderboard report
Change Detection SYSU-CD SChanger-small F1 84.58 #1 of 12 Archive leaderboard report
Change Detection SYSU-CD SChanger-base F1 84.17 #2 of 12 Archive leaderboard report
Change Detection WHU-CD SChanger-base F1 93.20 #6 of 22 Archive leaderboard report
Change Detection WHU-CD SChanger-small F1 93.15 #7 of 22 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AttentionFocusSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections