# Tackling Few-Shot Segmentation in Remote Sensing via Inpainting Diffusion Model

arXiv: https://arxiv.org/abs/2503.03785 · HTML: https://mlsanity.com/paper/2503.03785/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 16 of its 33 references that are in the map.
- First posted on arXiv 5 Mar 2025.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 16 of 16)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation](https://mlsanity.com/paper/2012.07177/) (2020)
- [Paint by Example: Exemplar-based Image Editing with Diffusion Models](https://mlsanity.com/paper/2211.13227/) (2022)
- [RemoteCLIP: A Vision Language Foundation Model for Remote Sensing](https://mlsanity.com/paper/2306.11029/) (2023)
- [Generalized Few-shot Semantic Segmentation](https://mlsanity.com/paper/2010.05210/) (2020)
- [MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2305.13864/) (2023)
- [A Strong Baseline for Generalized Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2211.14126/) (2022)
- [Generalized Few-Shot Meets Remote Sensing: Discovering Novel Classes in Land Cover Mapping via Hybrid Semantic Segmentation Framework](https://mlsanity.com/paper/2404.12721/) (2024)
- [Class Similarity Transition: Decoupling Class Similarities and Imbalance from Generalized Few-shot Segmentation](https://mlsanity.com/paper/2404.05111/) (2024)
- [Learnable Prompt for Few-Shot Semantic Segmentation in Remote Sensing Domain](https://mlsanity.com/paper/2404.10307/) (2024)
- [Generalized Few-Shot Semantic Segmentation in Remote Sensing: Challenge and Benchmark](https://mlsanity.com/paper/2409.11227/) (2024)

## Built on by (most cited first, 5 of 5)

- [RSFAKE-1M: A Large-Scale Dataset for Detecting Diffusion-Generated Remote Sensing Forgeries](https://mlsanity.com/paper/2505.23283/) (2025)
- [SimLBR: Learning to Detect Fake Images by Learning to Detect Real Images](https://mlsanity.com/paper/2602.20412/) (2026)
- [Few-Shot Open-Vocabulary Remote Sensing Segmentation via Textual Inversion](https://mlsanity.com/paper/2607.25563/) (2026)
- [Towards a satellite image manipulation and deepfake localization benchmark dataset](https://mlsanity.com/paper/2608.04840/) (2026)
- [ELMZip: Onboard Satellite Image Compression via Extreme Learning Machines for Efficient Downlink](https://mlsanity.com/paper/2608.06942/) (2026)

## Abstract (arXiv)

Limited data is a common problem in remote sensing due to the high cost of obtaining annotated samples. In the few-shot segmentation task, models are typically trained on base classes with abundant annotations and later adapted to novel classes with limited examples. However, this often necessitates specialized model architectures or complex training strategies. Instead, we propose a simple approach that leverages diffusion models to generate diverse variations of novel-class objects within a given scene, conditioned by the limited examples of the novel classes. By framing the problem as an image inpainting task, we synthesize plausible instances of novel classes under various environments, effectively increasing the number of samples for the novel classes and mitigating overfitting. The generated samples are then assessed using a cosine similarity metric to ensure semantic consistency with the novel classes. Additionally, we employ Segment Anything Model (SAM) to segment the generated samples and obtain precise annotations. By using high-quality synthetic data, we can directly fine-tune off-the-shelf segmentation models. Experimental results demonstrate that our method significantly enhances segmentation performance in low-data regimes, highlighting its potential for real-world remote sensing applications.