mlsanityData to 7 Oct 2026

EarthVL: A Progressive Earth Vision-Language Understanding and Generation Framework

arXiv 2601.02783 ↗First posted 6 Jan 2026cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Earth vision has achieved milestones in geospatial object recognition but lacks exploration in object-relational reasoning, limiting comprehensive scene understanding. To address this, a progressive Earth vision-language understanding and generation framework is proposed, including a multi-task dataset (EarthVLSet) and a semantic-guided network (EarthVLNet). Focusing on city planning applications, EarthVLSet includes 10.9k sub-meter resolution remote sensing images, land-cover masks, and 761.5k textual pairs involving both multiple-choice and open-ended visual question answering (VQA) tasks. In an object-centric way, EarthVLNet is proposed to progressively achieve semantic segmentation, relational reasoning, and comprehensive understanding. The first stage involves land-cover segmentation to generate object semantics for VQA guidance. Guided by pixel-wise semantics, the object awareness based large language model (LLM) performs relational reasoning and knowledge summarization to generate the required answers. As for optimization, the numerical difference loss is proposed to dynamically add difference penalties, addressing the various objects' statistics. Three benchmarks, including semantic segmentation, multiple-choice, and open-ended VQA demonstrated the superiorities of EarthVLNet, yielding three future directions: 1) segmentation features consistently enhance VQA performance even in cross-dataset scenarios; 2) multiple-choice tasks show greater sensitivity to the vision encoder than to the language decoder; and 3) open-ended tasks necessitate advanced vision encoders and language decoders for an optimal performance. We believe this dataset and method will provide a beneficial benchmark that connects ''image-mask-text'', advancing geographical applications for Earth vision.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 67 of its 88 references that are in the map. First posted on arXiv 6 Jan 2026.

Builds on

67 of 88 references.

References · 67

  1. 2017Attention Is All You Needcited by 59,932
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2023Visual Instruction Tuningcited by 7,792
  7. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  8. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  9. 2017Squeeze-and-Excitation Networkscited by 4,763
  10. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  11. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  12. 2022A ConvNet for the 2020scited by 3,545
38 more
  1. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  2. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  3. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,855
  4. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,669
  5. 2015VQA: Visual Question Answeringcited by 2,489
  6. 2016Pyramid Scene Parsing Networkcited by 2,472
  7. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  8. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  9. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,219
  10. 2021Align before Fuse: Vision and Language Representation Learning with Momentum Distillationcited by 1,612
  11. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,552
  12. 2019LXMERT: Learning Cross-Modality Encoder Representations from Transformerscited by 1,548
  13. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,518
  14. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  15. 2017Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answeringcited by 1,310
  16. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,265
  17. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,224
  18. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  19. 2023Vision-Language Models for Vision Tasks: A Surveycited by 834
  20. 2017Remote Sensing Image Scene Classification: Benchmark and State of the Artcited by 791
  21. 2019Panoptic Feature Pyramid Networkscited by 644
  22. 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 636
  23. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 577
  24. 2017CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learningcited by 459
  25. 2016AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classificationcited by 343
  26. 2019Deep Modular Co-Attention Networks for Visual Question Answeringcited by 338
  27. 2019GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyondcited by 331
  28. 2023GeoChat: Grounded Large Vision-Language Model for Remote Sensingcited by 320
  29. 2015Stacked Attention Networks for Image Question Answeringcited by 273
  30. 2019ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed datacited by 260
  31. 2021LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentationcited by 259
  32. 2022SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentationcited by 252
  33. 2017LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentationcited by 212
  34. 2023RSGPT: A Remote Sensing Vision Language Model and Benchmarkcited by 204
  35. 2021Object Detection in Aerial Images: A Large-Scale Benchmark and Challengescited by 202
  36. 2020RSVQA: Visual Question Answering for Remote Sensing Datacited by 197
  37. 2018Compositional Attention Networks for Machine Reasoningcited by 183
  38. 2020FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understandingcited by 181

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026GeoEyes: On-Demand Visual Focusing for Evidence-Grounded Understanding of Ultra-High-Resolution Remote Sensing Imagerycited by 9
  2. 2026RSEdit: Text-Guided Image Editing for Remote Sensingcited by 1
  3. 2026Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understandingcited by 1
  4. 2026GeoVista: Visually Grounded Active Perception for Vision-Language Understanding of Ultra-High-Resolution Remote Sensing Imagescited by 0
  5. 2026GeoChrono: Benchmarking and Rethinking Long-Term Temporal Understanding in Remote Sensingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025GeoRSMLLM: A Multimodal Large Language Model for Vision-Language Tasks in Geoscience and Remote Sensing
  2. 2024VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding
  3. 2025SegEarth-R1: Geospatial Pixel Reasoning via Large Language Model
  4. 2026VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensing
  5. 2025LISAT: Language-Instructed Segmentation Assistant for Satellite Imagery
  6. 2026LongEarth-R1: Benchmarking and Aligning Vision-Language Models for Long-Horizon Earth Observation Reasoning
  7. 2025RSVLM-QA: A Benchmark Dataset for Remote Sensing Vision Language Model-based Question Answering
  8. 2026OmniEarth: A Benchmark for Evaluating Vision-Language Models in Geospatial Tasks