paper-with-me

Papers

Adapting Segment Anything Model for Change Detection in HR Remote Sensing Images

2023-09-04 · Lei Ding, Kun Zhu, Daifeng Peng, Hao Tang, Kuiwu Yang, Lorenzo Bruzzone

Vision Foundation Models (VFMs) such as the Segment Anything Model (SAM) allow zero-shot or interactive segmentation of visual contents, thus they are quickly applied in a variety of visual scenes. However, their direct use in many Remote Sensing (RS) applications is often unsatisfactory due to the special imaging characteristics of RS images. In this work, we aim to utilize the strong visual recognition capabilities of VFMs to improve the change detection of high-resolution Remote Sensing Images (RSIs). We employ the visual encoder of FastSAM, an efficient variant of the SAM, to extract visual representations in RS scenes. To adapt FastSAM to focus on some specific ground objects in the RS scenes, we propose a convolutional adaptor to aggregate the task-oriented change information. Moreover, to utilize the semantic representations that are inherent to SAM features, we introduce a task-agnostic semantic learning branch to model the semantic latent in bi-temporal RSIs. The resulting method, SAMCD, obtains superior accuracy compared to the SOTA methods and exhibits a sample-efficient learning ability that is comparable to semi-supervised CD methods. To the best of our knowledge, this is the first work that adapts VFMs for the CD of HR RSIs.

📄 PDF Abstract BibTeX arXiv:2309.01429

Code (1)

ggsding/sam-cd 공식 구현 pytorch

Tasks

Change DetectionInteractive Segmentation

Methods 이 논문이 사용한 방법론

SAM 설명 없음
Focus 설명 없음

Similar Papers 제목 키워드 기반

MergeSAM: Unsupervised change detection of remote sensing images based on the Segment Anything Model

2025-07-30 · Meiqi Hu, Lingzhi Lu, Chengxi Han, Xiaoping Liu arxiv

Recently, large foundation models trained on vast datasets have demonstrated exceptional capabilities in feature extraction and general feature representation. The ongoing advancements in deep learning-driven large model…

Object SegmentationChange Detection

Change Detection Between Optical Remote Sensing Imagery and Map Data via Segment Anything Model (SAM)

2024-01-17 · Hongruixuan Chen, Jian Song, Naoto Yokoya

Unsupervised multimodal change detection is pivotal for time-sensitive tasks and comprehensive multi-temporal Earth monitoring. In this study, we explore unsupervised multimodal change detection between two key remote se…

Change DetectionSegmentation

PeftCD: Leveraging Vision Foundation Models with Parameter-Efficient Fine-Tuning for Remote Sensing Change Detection

2025-09-11 · Sijun Dong, Yuxuan Hu, LiBo Wang, Geng Chen 외 arxiv

To tackle the prevalence of pseudo changes, the scarcity of labeled samples, and the difficulty of cross-domain generalization in multi-temporal and multi-source remote sensing imagery, we propose PeftCD, a change detect…

parameter-efficient fine-tuningDomain GeneralizationChange Detection

Unsupervised Change Detection Based on Image Reconstruction Loss with Segment Anything

2024-08-18 · Remote Sensing Letters 2024 8 · Hyeoncheol Noh, Jingi Ju, YuHyun Kim, Minwoo Kim 외

In remote sensing, change detection based on deep learning shows promising performance. However, collecting multi-temporal paired images for training a change detection model is costly. To solve this problem, unsupervise…

Change DetectionImage Reconstruction

SAM2-UNeXT: An Improved High-Resolution Baseline for Adapting Foundation Models to Downstream Segmentation Tasks

2025-08-05 · Xinyu Xiong, Zihuang Wu, Lei Zhang, Lei Lu 외 arxiv

Recent studies have highlighted the potential of adapting the Segment Anything Model (SAM) for various downstream tasks. However, constructing a more powerful and generalizable encoder to further enhance performance rema…

Dichotomous Image SegmentationSaliency DetectionObject Detection