# Masks Can Talk: Extracting Structured Text Information from Single-Modal Images for Remote Sensing Change Detection

arXiv: https://arxiv.org/abs/2605.07178 · HTML: https://mlsanity.com/paper/2605.07178/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 38 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Fully Convolutional Siamese Networks for Change Detection](https://mlsanity.com/paper/1810.08462/) (2018)
- [Remote Sensing Image Change Detection with Transformers](https://mlsanity.com/paper/2103.00208/) (2021)
- [A Transformer-Based Siamese Network for Change Detection](https://mlsanity.com/paper/2201.01293/) (2022)
- [ChangeMamba: Remote Sensing Change Detection With Spatiotemporal State Space Model](https://mlsanity.com/paper/2404.03425/) (2024)
- [Building Change Detection for Remote Sensing Images Using a Dual Task Constrained Deep Siamese Convolutional Network Model](https://mlsanity.com/paper/1909.07726/) (2019)
- [CDMamba: Incorporating Local Clues into Mamba for Remote Sensing Image Binary Change Detection](https://mlsanity.com/paper/2406.04207/) (2024)
- [Bi-Temporal Semantic Reasoning for the Semantic Change Detection in HR Remote Sensing Images](https://mlsanity.com/paper/2108.06103/) (2021)
- [RSCaMa: Remote Sensing Image Change Captioning with State Space Model](https://mlsanity.com/paper/2404.18895/) (2024)
- [Semantic-CD: Remote Sensing Image Semantic Change Detection towards Open-vocabulary Setting](https://mlsanity.com/paper/2501.06808/) (2025)
- [UniChange: Unifying Change Detection with Multimodal Large Language Model](https://mlsanity.com/paper/2511.02607/) (2025)
- [STNet: Spatial and Temporal feature fusion network for change detection in remote sensing images](https://mlsanity.com/paper/2304.11422/) (2023)
- [DDLNet: Boosting Remote Sensing Change Detection with Dual-Domain Learning](https://mlsanity.com/paper/2406.13606/) (2024)
- [CDXLSTM: Boosting Remote Sensing Change Detection with Extended Long Short-Term Memory](https://mlsanity.com/paper/2411.07863/) (2024)
- [Changes in Gaza: DINOv3-Powered Multi-Class Change Detection for Damage Assessment in Conflict Zones](https://mlsanity.com/paper/2511.19035/) (2025)
- [Multimodal Feature Fusion Network with Text Difference Enhancement for Remote Sensing Change Detection](https://mlsanity.com/paper/2509.03961/) (2025)

## Abstract (arXiv)

Remote sensing change detection is pivotal for urban monitoring, disaster assessment, and environmental resource management. Yet, unimodal deep learning methods frequently confuse genuine semantic changes with visually similar but irrelevant variations. Recent multimodal approaches incorporate text as auxiliary supervision, but their descriptions are either semantically coarse and unstructured or model-generated and thus noisy. Critically, all of them overlook a simple fact: fine-grained change semantics are already implicitly encoded in the ground-truth mask labels that come standard with every change detection dataset. These masks know where the change happened, what the land-cover types were before and after, how the transition occurred, and how many objects were involved. In this paper, we propose S2M, a framework that obtains structured textual features directly from change labels at zero additional annotation cost. Specifically, each change region is automatically transcribed into a semantic quadruple (where, what, how, how many) and converted into several fixed-template text descriptions, providing precise, dense, and noise-free multimodal supervision. We adopts a two-stage training strategy to fine-tune on remote sensing imagery firstly for robust domain-specific representation, after which a multimodal decoder with a bi-directional contrastive loss is introduced to achieve deep alignment between visual features and structured textual embeddings. To validate our method, we construct Gaza-Change-v2, a new multi-class change detection (MCD) dataset about the Gaza Strip. On this MCD dataset, S2M achieves a Sek of 17.80% and an Fscd of 66.14%, notably surpassing even multimodal methods that leverage large language models. Our work demonstrates that masks can indeed talk. They tell us exactly what, where, how, and how many changes have occurred.