mlsanityData to 7 Oct 2026

Enhancing Remote Sensing Vision-Language Models for Zero-Shot Scene Classification

arXiv 2409.00698 ↗First posted 1 Sep 2024cs.CVcited by 8

On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models

Abstract (arXiv)

Vision-Language Models for remote sensing have shown promising uses thanks to their extensive pretraining. However, their conventional usage in zero-shot scene classification methods still involves dividing large images into patches and making independent predictions, i.e., inductive inference, thereby limiting their effectiveness by ignoring valuable contextual information. Our approach tackles this issue by utilizing initial predictions based on text prompting and patch affinity relationships from the image encoder to enhance zero-shot capabilities through transductive inference, all without the need for supervision and at a minor computational cost. Experiments on 10 remote sensing datasets with state-of-the-art Vision-Language Models demonstrate significant accuracy improvements over inductive zero-shot classification. Our source code is publicly available on Github: https://github.com/elkhouryk/RS-TransCLIP

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 25 of its 45 references that are in the map. First posted on arXiv 1 Sep 2024.

Builds on

25 of 45 references.

Closest ancestors · 9

Same direction, newest first

  1. 2024SkySenseGPT: A Fine-Grained Instruction Tuning Dataset and Model for Remote Sensing Vision-Language Understanding14 Jun
  2. 2024LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model4 Feb
  3. 2024EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain30 Jan
  4. 2023SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing20 Dec
  5. 2023Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment12 Dec
  6. 2023RSGPT: A Remote Sensing Vision Language Model and Benchmark28 Jul
  7. 2023RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing20 Jun
  8. 2023RemoteCLIP: A Vision Language Foundation Model for Remote Sensing19 Jun
  9. 2023Vision-Language Models in Remote Sensing: Current Progress and Future Trends9 May

Other references · 16

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2017Remote Sensing Image Scene Classification: Benchmark and State of the Artcited by 791
  3. 2023BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairscited by 506
  4. 2016AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classificationcited by 343
  5. 2019A Baseline for Few-Shot Image Classificationcited by 298
  6. 2015Learning Visual Features from Large Weakly Supervised Datacited by 165
  7. 2020Learning Visual Representations with Caption Annotationscited by 123
  8. 2017PatternNet: A Benchmark Dataset for Performance Evaluation of Remote Sensing Image Retrievalcited by 96
  9. 2019Prototype Rectification for Few-Shot Learningcited by 96
  10. 2020Laplacian Regularized Few-Shot Learningcited by 90
  11. 2021Does CLIP Benefit Visual Question Answering in the Medical Domain as Much as it Does in the General Domain?cited by 85
  12. 2024On the test-time zero-shot generalization of vision-language models: Do we really need prompt learning?cited by 65
4 more
  1. 2020MLRSNet: A Multi-label High Spatial Resolution Remote Sensing Dataset for Semantic Scene Understandingcited by 59
  2. 2024Boosting Vision-Language Models with Transductioncited by 36
  3. 2024Transductive Zero-Shot and Few-Shot CLIPcited by 31
  4. 2024Streamlined Hybrid Annotation Framework using Scalable Codestream for Bandwidth-Restricted UAV Object Detectioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 2.

8 papers.

  1. 2025Vision-Language Modeling Meets Remote Sensing: Models, Datasets and Perspectivescited by 18
  2. 2025Realistic Test-Time Adaptation of Vision-Language Modelscited by 14
  3. 2025Online Gaussian Test-Time Adaptation of Vision-Language Modelscited by 6
  4. 2025Survey of Multimodal Geospatial Foundation Models: Techniques, Applications, and Challengescited by 3
  5. 2025Few-Shot Adaptation Benchmark for Remote Sensing Vision-Language Modelscited by 1
  6. 2026Leveraging Prediction Entropy for Automatic Prompt Weighting in Zero-Shot Audio-Language Classificationcited by 1
  7. 2026Locally Consistent Transductive Information Maximization for Few-Shot Remote Sensing Scene Classificationcited by 1
  8. 2025Language-Aware Information Maximization for Transductive Few-Shot CLIPcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Beyond Templates: Revisiting Zero-Shot Remote Sensing through Meta-Prompting
  2. 2024Pushing the Limits of Vision-Language Models in Remote Sensing without Human Annotations
  3. 2024Deep Semantic-Visual Alignment for Zero-Shot Remote Sensing Image Scene Classification
  4. 2025Few-Shot Remote Sensing Image Scene Classification with CLIP and Prompt Learning
  5. 2025Quality-Driven Curation of Remote Sensing Vision-Language Data via Learned Scoring Models
  6. 2026Enabling Training-Free Text-Based Remote Sensing Segmentation
  7. 2025RSVG-ZeroOV: Exploring a Training-Free Framework for Zero-Shot Open-Vocabulary Visual Grounding in Remote Sensing Images
  8. 2025A Recipe for Improving Remote Sensing VLM Zero Shot Generalization