CoChat

EarthGPT: A Universal Multimodal Large Language Model for Multisensor Image Comprehension in Remote Sensing Domain

Open access
Zhang, Wei, Cai, Miaoxin, Zhang, Tong, Zhuang, Yin, Mao, Xuerui · 2024 · IEEE Transactions on Geoscience and Remote Sensing
Cited by 185

The DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.

Abstract

Multi-modal large language models (MLLMs) have demonstrated remarkable success in vision and visual-language tasks within the natural image domain. Owing to the significant domain gap between natural and remote sensing (RS) images, the development of MLLMs in the RS domain is still in the infant stage. To fill the gap, a pioneer MLLM named EarthGPT integrating various multi-sensor RS interpretation tasks uniformly is proposed in this paper for universal RS image comprehension. Firstly, a visual-enhanced perception mechanism is constructed to refine and incorporate coarse-scale semantic perception information and fine-scale detailed perception information. Secondly, a cross-modal mutual comprehension approach is proposed, aiming at enhancing the interplay between visual perception and language comprehension and deepening the comprehension of both visual and language content. Finally, a unified instruction tuning method for multi-sensor multi-task in the RS domain is proposed to unify a wide range of tasks including scene classification, image captioning, region-level captioning, visual question answering (VQA), visual grounding, object detection, etc. More importantly, a dataset named MMRS-1M featuring large-scale multi-sensor multi-modal RS instruction-following is constructed, comprising over 1M image-text pairs based on 34 existing diverse RS datasets and including multi-sensor images such as optical, synthetic aperture radar (SAR), and infrared. The MMRS-1M dataset addresses the drawback of MLLMs on RS expert knowledge and stimulates the development of MLLMs in the RS domain. Extensive experiments are conducted, demonstrating the EarthGPT’s superior performance in various RS visual interpretation tasks compared with the other specialist models and MLLMs, proving the effectiveness of the proposed EarthGPT and offering a versatile paradigm for open-set reasoning tasks. Our code and dataset are available at https://github.com/wivizhang/EarthGPT.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tgrs.2024.3409624

Cites

29 of 29 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 29 references

Research works printed but not linked: 76

  1. 10.3390/rs14225675 · DOI
  2. 10.1109/CVPR52688.2022.01750 · DOI · Paper page
  3. Dosovitskiy, 2020, An image is worth 16×16 words: Transformers for image recognition at scale, arXiv:2010.11929 · arXiv
  4. 10.48550/ARXIV.1511.08458 · arXiv · doi:10.48550/arxiv.1511.08458 · Paper page
  5. 10.1109/TGRS.2022.3201474 · DOI
  6. 10.1109/TGRS.2023.3312479 · DOI
  7. 10.3390/s20041226 · DOI
  8. 10.1109/JSTARS.2021.3063096 · DOI
  9. 10.11834/jrs.20222139 · DOI
  10. Achiam, 2023, GPT-4 technical report
  11. Zhang, 2023, LLaMA-adapter: Efficient fine-tuning of language models with zero-init attention, arXiv:2303.16199 · arXiv
  12. Peng, 2023, Instruction tuning with GPT-4, arXiv:2304.03277 · arXiv
  13. Gao, 2023, LLaMA-adapter v2: Parameter-efficient visual instruction model, arXiv:2304.15010 · arXiv
  14. Ye, 2023, MPLUG-owl: Modularization empowers large language models with multimodality, arXiv:2304.14178 · arXiv
  15. Lyu, 2023, Macaw-LLM: Multi-modal language modeling with image, audio, video, and text integration, arXiv:2306.09093 · arXiv
  16. Tang, 2023, CoDi-2: In-context, interleaved, and interactive any-to-any generation, arXiv:2311.18775 · arXiv
  17. Xu, 2023, PointLLM: Empowering large language models to understand point clouds, arXiv:2308.16911 · arXiv
  18. Guo, 2023, Point-bind & point-LLM: Aligning point cloud with multi-modality for 3D understanding, generation, and instruction following, arXiv:2309.00615 · arXiv
  19. Hong, 2023, 3D-LLM: Injecting the 3D world into large language models, arXiv:2307.12981 · arXiv
  20. Yang, 2023, LiDAR-LLM: Exploring the potential of large language models for 3D LiDAR understanding, arXiv:2312.14074 · arXiv
  21. Ahn, 2024, AutoRT: Embodied foundation models for large scale orchestration of robotic agents, arXiv:2401.12963 · arXiv
  22. Dai, 2023, InstructBLIP: Towards general-purpose vision-language models with instruction tuning, arXiv:2305.06500 · arXiv
  23. 10.1109/JSTARS.2021.3117857 · DOI
  24. 10.1109/TGRS.2023.3295797 · DOI
  25. 10.1109/TGRS.2022.3190934 · DOI
  26. 10.1109/TGRS.2021.3081421 · DOI
  27. 10.1109/LGRS.2019.2893772 · DOI
  28. 10.3390/rs11060612 · DOI · Paper page
  29. 10.1109/CVPR.2019.00331 · DOI · Paper page
  30. 10.1109/TGRS.2020.2988782 · DOI · Paper page
  31. 10.1109/CVPR.2016.538 · DOI · Paper page
  32. 10.1109/ICCV.2019.00479 · DOI
  33. 10.1109/ICCV.2019.00478 · DOI · Paper page
  34. 10.1109/CVPR46437.2021.01661 · DOI
  35. 10.1109/ICCV48922.2021.00179 · DOI · Paper page
  36. 10.1109/TGRS.2021.3062048 · DOI · Paper page
  37. 10.1109/CVPR46437.2021.00868 · DOI · Paper page
  38. 10.1109/ICCV48922.2021.00350 · DOI · Paper page
  39. 10.1609/aaai.v35i4.16426 · DOI · Paper page
  40. 10.1609/aaai.v36i1.19975 · DOI · Paper page
  41. 10.1109/TGRS.2017.2685945 · DOI · Paper page
  42. 10.1109/JPROC.2017.2675998 · DOI · Paper page
  43. 10.1145/1869790.1869829 · DOI · Paper page
  44. 10.1109/LGRS.2010.2055033 · DOI · Paper page
  45. 10.1109/TGRS.2014.2374218 · DOI · Paper page
  46. 10.1016/j.isprsjprs.2021.12.004 · DOI · Paper page
  47. 10.1109/TGRS.2019.2900302 · DOI · Paper page
  48. 10.1109/TGRS.2017.2778300 · DOI · Paper page
  49. 10.12000/JR19097 · DOI
  50. 10.1109/ACCESS.2020.3005861 · DOI · Paper page
  51. 10.3390/rs13183690 · DOI · Paper page
  52. Zamir, iSAID: A large-scale dataset for instance segmentation in aerial images, 28
  53. Wang, LoveDA: A remote sensing land-cover dataset for domain adaptive semantic segmentation, 1
  54. 10.1109/CITS.2016.7546397 · DOI · Paper page
  55. 10.1109/TGRS.2017.2776321 · DOI · Paper page
  56. 10.1109/TGRS.2021.3078451 · DOI · Paper page
  57. 10.1109/ACCESS.2021.3090981 · DOI · Paper page
  58. Chen, 2023, MiniGPT-v2: Large language model as a unified interface for vision-language multi-task learning, arXiv:2310.09478 · arXiv
  59. Lin, 2023, SPHINX: The joint mixing of weights, tasks, and visual embeddings for multi-modal large language models, arXiv:2311.07575 · arXiv
  60. 10.18653/v1/D18-2012 · DOI · Paper page
  61. 10.1109/LGRS.2015.2475299 · DOI · Paper page
  62. 10.3390/rs13040747 · DOI
  63. 10.1117/12.2532741 · DOI
  64. 10.1109/TGRS.2016.2645610 · DOI · Paper page
  65. 10.1038/s41597-023-02066-6 · DOI · Paper page
  66. 2021, Sea-Shipping
  67. 2021, Infrared-Security
  68. 2021, Aerial-Mancar
  69. 2021, Double-Light-Vehicle
  70. 2020, Oceanic-Ship
  71. Ilharco, 2021, OpenCLIP, Zenodo
  72. 10.1007/978-3-030-58568-6_23 · DOI · Paper page
  73. 10.1109/CVPR52688.2022.00928 · DOI · Paper page
  74. Zhao, 2024, An open and comprehensive pipeline for unified object grounding and detection, arXiv:2401.02361 · arXiv
  75. Wei, 2023, Lenna: Language enhanced reasoning detection assistant, arXiv:2312.02433 · arXiv
  76. 10.1109/CVPR52688.2022.00187 · DOI · Paper page

Cited by

See all 185

Metadata

Authors
Zhang, W., Cai, M., Zhang, T., Zhuang, Y., & Mao, X.
Venue
IEEE Transactions on Geoscience and Remote Sensing
Published
2024
Volume
62
Pages
1-20
ISSN
  • 0196-2892 (ISSN-L)
  • 1558-0644
OpenAlex
W4399399400
Cited by
185
References
29
FWCI
26.13
Type
journal article
Language
en
Open access
green
Funders
  • National Natural Science Foundation of China (92152109)
  • General Program of National Natural Science Foundation of China (62371048)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: EarthGPT: A Universal Multimodal Large Language Model for Multisensor Image Comprehension in Remote Sensing Domain. https://app.cochat.ai/papers/10.1109/tgrs.2024.3409624
The paper
Zhang, W., Cai, M., Zhang, T., Zhuang, Y., & Mao, X. (2024). EarthGPT: A Universal Multimodal Large Language Model for Multisensor Image Comprehension in Remote Sensing Domain. IEEE Transactions on Geoscience and Remote Sensing. https://doi.org/10.1109/tgrs.2024.3409624

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.