# AeroLite: Tag-Guided Lightweight Generation of Aerial Image Captions

arXiv: https://arxiv.org/abs/2504.09528 · HTML: https://mlsanity.com/paper/2504.09528/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 57 references that are in the map.
- First posted on arXiv 13 Apr 2025.

## Builds on (most cited first, 25 of 25)

- [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)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [Show and Tell: A Neural Image Caption Generator](https://mlsanity.com/paper/1411.4555/) (2014)
- [Hallucination of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2404.18930/) (2024)
- [RemoteCLIP: A Vision Language Foundation Model for Remote Sensing](https://mlsanity.com/paper/2306.11029/) (2023)
- [Meshed-Memory Transformer for Image Captioning](https://mlsanity.com/paper/1912.08226/) (2019)
- [GeoChat: Grounded Large Vision-Language Model for Remote Sensing](https://mlsanity.com/paper/2311.15826/) (2023)
- [LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2110.08733/) (2021)
- [RSGPT: A Remote Sensing Vision Language Model and Benchmark](https://mlsanity.com/paper/2307.15266/) (2023)
- [Exploring Models and Data for Remote Sensing Image Caption Generation](https://mlsanity.com/paper/1712.07835/) (2017)
- [VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding](https://mlsanity.com/paper/2406.12384/) (2024)
- [A Review on Edge Large Language Models: Design, Execution, and Applications](https://mlsanity.com/paper/2410.11845/) (2024)
- [Benchmarking and Improving Detail Image Caption](https://mlsanity.com/paper/2405.19092/) (2024)
- [BTLM-3B-8K: 7B Parameter Performance in a 3B Parameter Model](https://mlsanity.com/paper/2309.11568/) (2023)
- [TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training](https://mlsanity.com/paper/2312.12828/) (2023)
- [A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future](https://mlsanity.com/paper/2412.14056/) (2024)
- [CapText: Large Language Model-based Caption Generation From Image Context and Description](https://mlsanity.com/paper/2306.00301/) (2023)

## Abstract (arXiv)

Accurate and automated captioning of aerial imagery is crucial for applications like environmental monitoring, urban planning, and disaster management. However, this task remains challenging due to complex spatial semantics and domain variability. To address these issues, we introduce AeroLite, a lightweight, tag-guided captioning framework designed to equip small-scale language models (1--3B parameters) with robust and interpretable captioning capabilities specifically for remote sensing images. AeroLite leverages GPT-4o to generate a large-scale, semantically rich pseudo-caption dataset by integrating multiple remote sensing benchmarks, including DLRSD, iSAID, LoveDA, WHU, and RSSCN7. To explicitly capture key semantic elements such as orientation and land-use types, AeroLite employs natural language processing techniques to extract relevant semantic tags. These tags are then learned by a dedicated multi-label CLIP encoder, ensuring precise semantic predictions. To effectively fuse visual and semantic information, we propose a novel bridging multilayer perceptron (MLP) architecture, aligning semantic tags with visual embeddings while maintaining minimal computational overhead. AeroLite's flexible design also enables seamless integration with various pretrained large language models. We adopt a two-stage LoRA-based training approach: the initial stage leverages our pseudo-caption dataset to capture broad remote sensing semantics, followed by fine-tuning on smaller, curated datasets like UCM and Sydney Captions to refine domain-specific alignment. Experimental evaluations demonstrate that AeroLite surpasses significantly larger models (e.g., 13B parameters) in standard captioning metrics, including BLEU and METEOR, while maintaining substantially lower computational costs.