Locate Anything on Earth: Advancing Open-Vocabulary Object Detection for Remote Sensing Community

AAAI 2025

Jiancheng Pan^*1,2,

Yanxing Liu^*3,

Yuqian Fu†^4,5,

Muyuan Ma¹,

Jiaohao Li¹,

Danda Pani Paudel^4,5, Luc Van Gool^4,5, Xiaomeng Huang†¹,

¹Tsinghua University, ²Zhejiang University of Technology, ³University of Chinese Academy of Sciences, ⁴ETH Zürich, ⁵INSAIT

arXiv Data & Code Video

Locate Anything on Earth (LAE) aims to detect any object on Earth and facilitate practical detection tasks, powered by LAE-Label Engine and LAE-DINO Model.

Motivations

Object detection, particularly open-vocabulary object detection, plays a crucial role in Earth sciences, such as environmental monitoring, natural disaster assessment, and landuse planning. However, existing open-vocabulary detectors, primarily trained on natural-world images, struggle to generalize to remote sensing images due to a significant data domain gap. Thus, this paper aims to advance the development of open-vocabulary object detection in remote sensing community.

Contributions

🌍 LAE-1M Dataset powered by LAE-Label Engine

LAE-Label engine is proposed to solve the lack of diverse object-level labeled data in the remote sensing community, which is essentially an indispensable part of training robust foundation models.
LAE-1M dataset is get by the LAE-Label engine with one million labeled objects across diverse categories.

🛰️ LAE-DINO Open-Vocabulary Detector

LAE-DINO Model is proposed and trained to work as the first foundation models for the newly proposed LAE task.

LAE-1M Dataset

In addition to the visual examples as shown in the benchmark figure, we further provide more infomations here. All the target datasets could be found on our github repo.

LAE-COD dataset examples: Raw data labelled by LAE-Label engine without rule-based filtering.

LAE-DINO Model

We propose a novel LAE-DINO detector for LAE, with dynamic vocaublary constuction (DVC) and VisualGuided Text Prompt Learning (VisGT) as novel modules. The Overall framework of our LAE-DINO:

Citation

Please consider cite us if you find our dataset, or model is useful to you.


      @misc{pan2024locateearthadvancingopenvocabulary,
        title={Locate Anything on Earth: Advancing Open-Vocabulary Object Detection for Remote Sensing Community}, 
        author={Jiancheng Pan and Yanxing Liu and Yuqian Fu and Muyuan Ma and Jiaohao Li and Danda Pani Paudel and Luc Van Gool and Xiaomeng Huang},
        year={2024},
        eprint={2408.09110},
        archivePrefix={arXiv},
        primaryClass={cs.CV},
        url={https://arxiv.org/abs/2408.09110}, 
    }