# SIGMAE: A Spectral-Index-Guided Foundation Model for Multispectral Remote Sensing

arXiv: https://arxiv.org/abs/2603.07463 · HTML: https://mlsanity.com/paper/2603.07463/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 53 references that are in the map.
- First posted on arXiv 8 Mar 2026.

## Builds on (most cited first, 30 of 30)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [Functional Map of the World](https://mlsanity.com/paper/1711.07846/) (2017)
- [Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning](https://mlsanity.com/paper/2212.14532/) (2022)
- [MultiMAE: Multi-modal Multi-task Masked Autoencoders](https://mlsanity.com/paper/2204.01678/) (2022)
- [SpectralGPT: Spectral Remote Sensing Foundation Model](https://mlsanity.com/paper/2311.07113/) (2023)
- [BigEarthNet: A Large-Scale Benchmark Archive For Remote Sensing Image Understanding](https://mlsanity.com/paper/1902.06148/) (2019)
- [SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery](https://mlsanity.com/paper/2312.10115/) (2023)
- [CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders](https://mlsanity.com/paper/2311.00566/) (2023)
- [SatlasPretrain: A Large-Scale Dataset for Remote Sensing Image Understanding](https://mlsanity.com/paper/2211.15660/) (2022)
- [Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model](https://mlsanity.com/paper/2208.03987/) (2022)
- [Foundation Models for Generalist Geospatial Artificial Intelligence](https://mlsanity.com/paper/2310.18660/) (2023)
- [Land-Cover Classification with High-Resolution Remote Sensing Images Using Transferable Deep Models](https://mlsanity.com/paper/1807.05713/) (2018)
- [SemMAE: Semantic-Guided Masking for Learning Masked Autoencoders](https://mlsanity.com/paper/2206.10207/) (2022)
- [Urban Change Detection for Multispectral Earth Observation Using Convolutional Neural Networks](https://mlsanity.com/paper/1810.08468/) (2018)
- [Towards Geospatial Foundation Models via Continual Pretraining](https://mlsanity.com/paper/2302.04476/) (2023)
- [Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery](https://mlsanity.com/paper/2403.05419/) (2024)
- [MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining](https://mlsanity.com/paper/2403.13430/) (2024)
- [Beyond RGB: Very High Resolution Urban Remote Sensing With Multimodal Deep Networks](https://mlsanity.com/paper/1711.08681/) (2017)
- [Vision Foundation Models in Remote Sensing: A Survey](https://mlsanity.com/paper/2408.03464/) (2024)
- [Feature Guided Masked Autoencoder for Self-supervised Learning in Remote Sensing](https://mlsanity.com/paper/2310.18653/) (2023)
- [Bridging Remote Sensors with Multisensor Geospatial Foundation Models](https://mlsanity.com/paper/2404.01260/) (2024)
- [Self-supervised remote sensing feature learning: Learning Paradigms, Challenges, and Future Works](https://mlsanity.com/paper/2211.08129/) (2022)
- [FlexiMo: A Flexible Remote Sensing Foundation Model](https://mlsanity.com/paper/2503.23844/) (2025)
- [Improving Masked Autoencoders by Learning Where to Mask](https://mlsanity.com/paper/2303.06583/) (2023)
- [The Outcome of the 2022 Landslide4Sense Competition: Advanced Landslide Detection from Multi-Source Satellite Imagery](https://mlsanity.com/paper/2209.02556/) (2022)
- [RingMo-Aerial: An Aerial Remote Sensing Foundation Model With Affine Transformation Contrastive Learning](https://mlsanity.com/paper/2409.13366/) (2024)
- [Geospatial Foundation Models to Enable Progress on Sustainable Development Goals](https://mlsanity.com/paper/2505.24528/) (2025)
- [Robust Burned Area Delineation through Multitask Learning](https://mlsanity.com/paper/2309.08368/) (2023)

## Built on by (most cited first, 1 of 1)

- [Earth Observation Foundation Models for Terrestrial Ecohydrology: From Representation Learning to Process Inference](https://mlsanity.com/paper/2608.15282/) (2026)

## Abstract (arXiv)

Pretraining and fine-tuning have emerged as a new paradigm in remote sensing image interpretation. Among them, Masked Autoencoder (MAE)-based pretraining stands out for its strong capability to learn general feature representations via reconstructing masked image regions. However, applying MAE to multispectral remote sensing images remains challenging due to complex backgrounds, indistinct targets, and the lack of semantic guidance during masking, which hinders the learning of underlying structures and meaningful spatial-spectral features. To address this, we propose a simple yet effective approach, Spectral Index-Guided MAE (SIGMAE), for multispectral image pretraining. The core idea is to incorporate domain-specific spectral indices as prior knowledge to guide dynamic token masking toward informative regions. SIGMAE introduces Semantic Saliency-Guided Dynamic Token Masking (SSDTM), a curriculum-style strategy that quantifies each patch's semantic richness and internal heterogeneity to adaptively select the most informative tokens during training. By prioritizing semantically salient regions and progressively increasing sample difficulty, SSDTM enhances spectrally rich and structurally aware representation learning, mitigates overfitting, and reduces redundant computation compared with random masking. Extensive experiments on five widely used datasets covering various downstream tasks, including scene classification, semantic segmentation, object extraction and change detection, demonstrate that SIGMAE outperforms other pretrained geospatial foundation models. Moreover, it exhibits strong spatial-spectral reconstruction capability, even with a 90% mask ratio, and improves complex target recognition under limited labeled data. The source codes and model weights will be released at https://github.com/zxk688/SIGMAE.