Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Segment Change Model (SCM) for Unsupervised Change detection in VHR Remote Sensing Images: a Case Study of Buildings

About

The field of Remote Sensing (RS) widely employs Change Detection (CD) on very-high-resolution (VHR) images. A majority of extant deep-learning-based methods hinge on annotated samples to complete the CD process. Recently, the emergence of Vision Foundation Model (VFM) enables zero-shot predictions in particular vision tasks. In this work, we propose an unsupervised CD method named Segment Change Model (SCM), built upon the Segment Anything Model (SAM) and Contrastive Language-Image Pre-training (CLIP). Our method recalibrates features extracted at different scales and integrates them in a top-down manner to enhance discriminative change edges. We further design an innovative Piecewise Semantic Attention (PSA) scheme, which can offer semantic representation without training, thereby minimize pseudo change phenomenon. Through conducting experiments on two public datasets, the proposed SCM increases the mIoU from 46.09% to 53.67% on the LEVIR-CD dataset, and from 47.56% to 52.14% on the WHU-CD dataset. Our codes are available at https://github.com/StephenApX/UCD-SCM.

Xiaoliang Tan, Guanzhou Chen, Tong Wang, Jiaqi Wang, Xiaodong Zhang• 2023

Related benchmarks

TaskDatasetResultRank
Change DetectionLEVIR-CD (test)
F1 Score31.7
503
Change DetectionWHU-CD (test)--
392
Change DetectionLEVIR-CD
F1 Score62.8
308
Change DetectionWHU-CD
IoU19.14
278
Building Change DetectionWHU-CD (test)
IoU (Changed)21.57
55
Change DetectionWHU-CD
mIoU52.1
55
Remote Sensing Change DetectionCLCD
F1 Score23.31
44
Change DetectionAvg across SYSU, LEVIR, GVLM, CLCD, OSCD
Precision21.6
23
Building Change DetectionDSIFN (test)
IoU^c15.89
20
Unsupervised Change DetectionGVLM
F1 Score28
12
Showing 10 of 25 rows

Other info

Follow for update