Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
126 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Generalized Few-Shot Meets Remote Sensing: Discovering Novel Classes in Land Cover Mapping via Hybrid Semantic Segmentation Framework (2404.12721v1)

Published 19 Apr 2024 in cs.CV, cs.AI, and cs.LG

Abstract: Land-cover mapping is one of the vital applications in Earth observation, aiming at classifying each pixel's land-cover type of remote-sensing images. As natural and human activities change the landscape, the land-cover map needs to be rapidly updated. However, discovering newly appeared land-cover types in existing classification systems is still a non-trivial task hindered by various scales of complex land objects and insufficient labeled data over a wide-span geographic area. In this paper, we propose a generalized few-shot segmentation-based framework, named SegLand, to update novel classes in high-resolution land-cover mapping. Specifically, the proposed framework is designed in three parts: (a) Data pre-processing: the base training set and the few-shot support sets of novel classes are analyzed and augmented; (b) Hybrid segmentation structure; Multiple base learners and a modified Projection onto Orthogonal Prototypes (POP) network are combined to enhance the base-class recognition and to dig novel classes from insufficient labels data; (c) Ultimate fusion: the semantic segmentation results of the base learners and POP network are reasonably fused. The proposed framework has won first place in the leaderboard of the OpenEarthMap Land Cover Mapping Few-Shot Challenge. Experiments demonstrate the superiority of the framework for automatically updating novel land-cover classes with limited labeled data.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (49)
  1. Large scale high-resolution land cover mapping with multi-resolution data. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12726–12735, 2019.
  2. Land-cover classification with high-resolution remote sensing images using transferable deep models. Remote Sensing of Environment, 237:111322, 2020.
  3. The outcome of the 2021 ieee grss data fusion contest—track msd: Multitemporal semantic change detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15:1643–1655, 2022.
  4. Polygonal building extraction by frame field learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5891–5900, 2021.
  5. Seamless and automated rapeseed mapping for large cloudy regions using time-series optical satellite imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 184:45–62, 2022.
  6. Jonathan Cheung-Wai Chan and Desiré Paelinckx. Evaluation of random forest and adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery. Remote Sensing of Environment, 112(6):2999–3011, 2008.
  7. Luojia-hssr: A high spatial-spectral resolution remote sensing dataset for land-cover classification with a new 3d-hrnet. Geo-spatial Information Science, pages 1–13, 2022.
  8. Unetformer: A unet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 190:196–214, 2022.
  9. A novel transformer based semantic segmentation scheme for fine-resolution remote sensing images. IEEE Geoscience and Remote Sensing Letters, 19:1–5, 2022.
  10. Submeter-level land cover mapping of japan. International Journal of Applied Earth Observation and Geoinformation, 127:103660, 2024.
  11. Sinolc-1: the first 1 m resolution national-scale land-cover map of china created with a deep learning framework and open-access data. Earth System Science Data, 15(11):4749–4780, 2023.
  12. Esa worldcover: Global land cover mapping at 10 m resolution for 2020 based on sentinel-1 and 2 data. In AGU Fall Meeting Abstracts, volume 2021, pages GC45I–0915, 2021.
  13. Generalized few-shot semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11563–11572, 2022.
  14. Cross-sensor domain adaptation for high spatial resolution urban land-cover mapping: From airborne to spaceborne imagery. Remote Sensing of Environment, 277:113058, 2022.
  15. Openearthmap: A benchmark dataset for global high-resolution land cover mapping. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 6254–6264, 2023.
  16. Learning what not to segment: A new perspective on few-shot segmentation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 8057–8067, 2022.
  17. Generalized few-shot semantic segmentation: All you need is fine-tuning. arXiv preprint arXiv:2112.10982, 2021.
  18. A strong baseline for generalized few-shot semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11269–11278, 2023.
  19. Prediction calibration for generalized few-shot semantic segmentation. IEEE transactions on image processing, 2023.
  20. Learning orthogonal prototypes for generalized few-shot semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11319–11328, 2023.
  21. A global reference database from very high resolution commercial satellite data and methodology for application to landsat derived 30 m continuous field tree cover data. Remote sensing of environment, 165:234–248, 2015.
  22. High-resolution land cover mapping through learning with noise correction. IEEE Transactions on Geoscience and Remote Sensing, 60:1–13, 2021.
  23. Pierre Defourny et al. GLOBCOVER: a 300 m global land cover product for 2005 using envisat meris time series. In Proceedings of ISPRS Commission VII Mid-Term Symposium, pages 8–11. Citeseer, 2006.
  24. Jun Chen et al. Global land cover mapping at 30 m resolution: A pok-based operational approach. ISPRS Journal of Photogrammetry and Remote Sensing, 103:7–27, 2015.
  25. Stable classification with limited sample: Transferring a 30-m resolution sample set collected in 2015 to mapping 10-m resolution global land cover in 2017. Sci. Bull, 64(370-373):3, 2019.
  26. Xin Huang et al. High-resolution urban land-cover mapping and landscape analysis of the 42 major cities in china using zy-3 satellite images. Science Bulletin, 65(12):1039–1048, 2020.
  27. Breaking the resolution barrier: A low-to-high network for large-scale high-resolution land-cover mapping using low-resolution labels. ISPRS Journal of Photogrammetry and Remote Sensing, 192:244–267, 2022.
  28. Learning without exact guidance: Updating large-scale high-resolution land cover maps from low-resolution historical labels. arXiv preprint arXiv:2403.02746, 2024.
  29. Minifrance, 2020.
  30. Multi-stage pseudo-label iteration framework for semi-supervised land-cover mapping. In IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium, pages 4607–4610. IEEE, 2022.
  31. Spatial–spectral relation network for hyperspectral image classification with limited training samples. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(12):5086–5100, 2019.
  32. Cross-domain meta-learning under dual adjustment mode for few-shot hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 2023.
  33. Class-balanced loss based on effective number of samples. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 9268–9277, 2019.
  34. Cutmix: Regularization strategy to train strong classifiers with localizable features. In Proceedings of the IEEE/CVF international conference on computer vision, pages 6023–6032, 2019.
  35. Deep high-resolution representation learning for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(10):3349–3364, 2021.
  36. Aggregated residual transformations for deep neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1492–1500, 2017.
  37. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning, pages 6105–6114. PMLR, 2019.
  38. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248–255. Ieee, 2009.
  39. Microsoft coco: Common objects in context. In Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pages 740–755. Springer, 2014.
  40. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
  41. Deep high-resolution representation learning for visual recognition. IEEE transactions on pattern analysis and machine intelligence, 43(10):3349–3364, 2020.
  42. Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF international conference on computer vision, pages 10012–10022, 2021.
  43. A convnet for the 2020s. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 11976–11986, 2022.
  44. Large selective kernel network for remote sensing object detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 16794–16805, 2023.
  45. Panoptic feature pyramid networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 6399–6408, 2019.
  46. Foreground-aware relation network for geospatial object segmentation in high spatial resolution remote sensing imagery. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 4096–4105, 2020.
  47. Unified perceptual parsing for scene understanding. In Proceedings of the European conference on computer vision (ECCV), pages 418–434, 2018.
  48. Pyramid scene parsing network. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2881–2890, 2017.
  49. Multimodal unsupervised domain adaptation for remote sensing image segmentation. In 2023 13th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS), pages 1–5, 2023.
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets