# Generalized Referring Expression Segmentation on Aerial Photos

arXiv: https://arxiv.org/abs/2512.07338 · HTML: https://mlsanity.com/paper/2512.07338/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 39 references that are in the map.
- First posted on arXiv 8 Dec 2025.

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

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [DOTA: A Large-scale Dataset for Object Detection in Aerial Images](https://mlsanity.com/paper/1711.10398/) (2017)
- [Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark](https://mlsanity.com/paper/1909.00133/) (2019)
- [LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2110.08733/) (2021)
- [Segmentation from Natural Language Expressions](https://mlsanity.com/paper/1603.06180/) (2016)
- [Tower: An Open Multilingual Large Language Model for Translation-Related Tasks](https://mlsanity.com/paper/2402.17733/) (2024)
- [iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images](https://mlsanity.com/paper/1905.12886/) (2019)
- [Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation](https://mlsanity.com/paper/2312.12470/) (2023)
- [RRSIS: Referring Remote Sensing Image Segmentation](https://mlsanity.com/paper/2306.08625/) (2023)
- [SegEarth-R1: Geospatial Pixel Reasoning via Large Language Model](https://mlsanity.com/paper/2504.09644/) (2025)
- [Exploring Fine-Grained Image-Text Alignment for Referring Remote Sensing Image Segmentation](https://mlsanity.com/paper/2409.13637/) (2024)
- [RSRefSeg: Referring Remote Sensing Image Segmentation with Foundation Models](https://mlsanity.com/paper/2501.06809/) (2025)
- [Intra- and Cross-Scale Feature Interaction Network for Referring Remote Sensing Image Segmentation](https://mlsanity.com/paper/2506.03583/) (2025)
- [Scale-wise Bidirectional Alignment Network for Referring Remote Sensing Image Segmentation](https://mlsanity.com/paper/2501.00851/) (2025)
- [Referring Remote Sensing Image Segmentation via Bidirectional Alignment Guided Joint Prediction](https://mlsanity.com/paper/2502.08486/) (2025)
- [SAM3-I: Segment Anything with Instructions](https://mlsanity.com/paper/2512.04585/) (2025)
- [WakeupUrban: Unsupervised Semantic Segmentation of Mid-20th century Urban Landscapes with Satellite Imagery](https://mlsanity.com/paper/2506.09476/) (2025)

## Built on by (most cited first, 2 of 2)

- [An Efficient and Effective Encoder Model for Vision and Language Tasks in the Remote Sensing Domain](https://mlsanity.com/paper/2512.15531/) (2025)
- [GeoSelect: Spatial-Program Execution for Training-Free Referring Remote Sensing Image Segmentation](https://mlsanity.com/paper/2607.03869/) (2026)

## Abstract (arXiv)

Referring expression segmentation is a fundamental task in computer vision that integrates natural language understanding with precise visual localization of target regions. Considering aerial imagery (e.g., modern aerial photos collected through drones, historical photos from aerial archives, high-resolution satellite imagery, etc.) presents unique challenges because spatial resolution varies widely across datasets, the use of color is not consistent, targets often shrink to only a few pixels, and scenes contain very high object densities and objects with partial occlusions. This work presents Aerial-D, a new large-scale referring expression segmentation dataset for aerial imagery, comprising 37,288 images with 1,522,523 referring expressions that cover 259,709 annotated targets, spanning across individual object instances, groups of instances, and semantic regions covering 21 distinct classes that range from vehicles and infrastructure to land coverage types. The dataset was constructed through a fully automatic pipeline that combines systematic rule-based expression generation with a Large Language Model (LLM) enhancement procedure that enriched both the linguistic variety and the focus on visual details within the referring expressions. Filters were additionally used to simulate historic imaging conditions for each scene. We adopted the RSRefSeg architecture, and trained models on Aerial-D together with prior aerial datasets, yielding unified instance and semantic segmentation from text for both modern and historical images. Results show that the combined training achieves competitive performance on contemporary benchmarks, while maintaining strong accuracy under monochrome, sepia, and grainy degradations that appear in archival aerial photography. The dataset, trained models, and complete software pipeline are publicly available at https://luispl77.github.io/aerial-d .