MSSDF: Modality-Shared Self-supervised Distillation for High-Resolution Multi-modal Remote Sensing Image Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Tong, Chen, Guanzhou, Zhang, Xiaodong, Liu, Chenxi, Wang, Jiaqi, Tan, Xiaoliang, Guo, Wenchao, Yang, Qingyuan, Zhang, Kaiqi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917219924967424
author Wang, Tong
Chen, Guanzhou
Zhang, Xiaodong
Liu, Chenxi
Wang, Jiaqi
Tan, Xiaoliang
Guo, Wenchao
Yang, Qingyuan
Zhang, Kaiqi
author_facet Wang, Tong
Chen, Guanzhou
Zhang, Xiaodong
Liu, Chenxi
Wang, Jiaqi
Tan, Xiaoliang
Guo, Wenchao
Yang, Qingyuan
Zhang, Kaiqi
contents Remote sensing image interpretation plays a critical role in environmental monitoring, urban planning, and disaster assessment. However, acquiring high-quality labeled data is often costly and time-consuming. To address this challenge, we proposes a multi-modal self-supervised learning framework that leverages high-resolution RGB images, multi-spectral data, and digital surface models (DSM) for pre-training. By designing an information-aware adaptive masking strategy, cross-modal masking mechanism, and multi-task self-supervised objectives, the framework effectively captures both the correlations across different modalities and the unique feature structures within each modality. We evaluated the proposed method on multiple downstream tasks, covering typical remote sensing applications such as scene classification, semantic segmentation, change detection, object detection, and depth estimation. Experiments are conducted on 15 remote sensing datasets, encompassing 26 tasks. The results demonstrate that the proposed method outperforms existing pretraining approaches in most tasks. Specifically, on the Potsdam and Vaihingen semantic segmentation tasks, our method achieved mIoU scores of 78.30\% and 76.50\%, with only 50\% train-set. For the US3D depth estimation task, the RMSE error is reduced to 0.182, and for the binary change detection task in SECOND dataset, our method achieved mIoU scores of 47.51\%, surpassing the second CS-MAE by 3 percentage points. Our pretrain code, checkpoints, and HR-Pairs dataset can be found in https://github.com/CVEO/MSSDF.
format Preprint
id arxiv_https___arxiv_org_abs_2506_09327
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MSSDF: Modality-Shared Self-supervised Distillation for High-Resolution Multi-modal Remote Sensing Image Learning
Wang, Tong
Chen, Guanzhou
Zhang, Xiaodong
Liu, Chenxi
Wang, Jiaqi
Tan, Xiaoliang
Guo, Wenchao
Yang, Qingyuan
Zhang, Kaiqi
Computer Vision and Pattern Recognition
Remote sensing image interpretation plays a critical role in environmental monitoring, urban planning, and disaster assessment. However, acquiring high-quality labeled data is often costly and time-consuming. To address this challenge, we proposes a multi-modal self-supervised learning framework that leverages high-resolution RGB images, multi-spectral data, and digital surface models (DSM) for pre-training. By designing an information-aware adaptive masking strategy, cross-modal masking mechanism, and multi-task self-supervised objectives, the framework effectively captures both the correlations across different modalities and the unique feature structures within each modality. We evaluated the proposed method on multiple downstream tasks, covering typical remote sensing applications such as scene classification, semantic segmentation, change detection, object detection, and depth estimation. Experiments are conducted on 15 remote sensing datasets, encompassing 26 tasks. The results demonstrate that the proposed method outperforms existing pretraining approaches in most tasks. Specifically, on the Potsdam and Vaihingen semantic segmentation tasks, our method achieved mIoU scores of 78.30\% and 76.50\%, with only 50\% train-set. For the US3D depth estimation task, the RMSE error is reduced to 0.182, and for the binary change detection task in SECOND dataset, our method achieved mIoU scores of 47.51\%, surpassing the second CS-MAE by 3 percentage points. Our pretrain code, checkpoints, and HR-Pairs dataset can be found in https://github.com/CVEO/MSSDF.
title MSSDF: Modality-Shared Self-supervised Distillation for High-Resolution Multi-modal Remote Sensing Image Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.09327