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

TL;DR

This paper introduces an unsupervised change detection method for very-high-resolution remote sensing images, leveraging foundation models to improve accuracy without requiring annotated training data.

Contribution

The proposed Segment Change Model (SCM) innovatively combines SAM and CLIP, with a novel PSA scheme, enabling effective unsupervised change detection in VHR images.

Findings

Achieved significant mIoU improvements on LEVIR-CD and WHU-CD datasets.

Demonstrated the effectiveness of zero-shot semantic features in change detection.

Provided open-source code for reproducibility.

Abstract

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.