CoChat
Sign Up
Cited by 33

The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.

Full-Level Domain Adaptation for Building Extraction in Very-High-Resolution Optical Remote-Sensing Images

Peng, Daifeng, Guan, Haiyan, Zang, Yufu, Bruzzone, Lorenzo·2022·IEEE Transactions on Geoscience and Remote Sensing
DOI 10.1109/tgrs.2021.3093004
Open this paper in CoChat — free account

Abstract

Convolutional neural networks (CNNs) have achieved tremendous success in computer vision tasks, such as building extraction. However, due to domain shift, the performance of the CNNs drops sharply on unseen data from another domain, leading to poor generalization. As it is costly and time-consuming to acquire dense annotations for remote-sensing (RS) images, developing algorithms that can transfer knowledge from a labeled source domain to an unlabeled target domain is of great significance. To this end, we propose a novel full-level domain adaptation network (FDANet) for building extraction by combining image-, feature-, and output-level information effectively. At the input level, a simple Wallis filter method is employed to transfer source images into target-like ones whereby alleviating radiometric discrepancy and achieving image-level alignment. To further reduce domain shift, adversarial learning is used to enforce feature distribution consistency constraints between the source and target images. In this way, feature-level alignment can be embedded effectively. At the output level, a mean-teacher model is introduced to enforce transformation-consistent constraint for the target output so that the regularization effect is enhanced and the uncertain predictions can be suppressed as much as possible. To further improve the performance, a novel self-training strategy is also employed by using pseudo labels. The effectiveness of the proposed FDANet is verified on three divers…

Overview

Integrity signals

Registry

Crossref · 10.1109/tgrs.2021.3093004

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Current pseudo-labeling approaches empirically choose a confidence threshold or set a fixed proportion for sample collection, which is hard to guarantee the accuracy of pseudo-labels assigned by the prediction model to its unknown domain.

    “The current approaches are empirically choosing a confidence threshold (Xu et al., 2020, Peng et al., 2021) or setting a fixed proportion for sample collection (Tong et al., 2020, Zhang et al., 2021a, Yan et al., 2019, Wang et al., 2022), which is hard to guarantee the accuracy of pseudo-labels assigned by the prediction model to its unknown domain.”

    From Enabling country-scale land cover mapping with meter-resolution satellite imagery (2023) · cites this paper as Peng et al., 2021

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 58

  1. 10.1016/j.isprsjprs.2013.06.011 · DOI
  2. 10.3390/rs10101512 · DOI
  3. 10.1109/TIP.2020.2988175 · DOI
  4. 10.1109/JSTARS.2011.2168195 · DOI
  5. 10.1109/TGRS.2012.2200689 · DOI
  6. 10.1109/TGRS.2008.2008440 · DOI
  7. 10.1109/TGRS.2014.2382566 · DOI
  8. 10.1016/j.cviu.2019.06.001 · DOI
  9. 10.1109/CVPR.2015.7298965 · DOI · Paper page
  10. 10.3390/rs11151774 · DOI
  11. 10.3390/rs11232813 · DOI
  12. 10.3390/rs12061050 · DOI
  13. 10.1109/TGRS.2020.3026051 · DOI
  14. Bonafilia, Building high resolution maps for humanitarian aid and development with weakly- and semi-supervised learning, 1
  15. 10.1109/LGRS.2019.2963065 · DOI
  16. 10.3390/rs13030371 · DOI
  17. Na, 2020, Domain adaptive transfer attack (DATA)-based segmentation networks for building extraction from aerial images
  18. 10.1109/LGRS.2020.3010591 · DOI
  19. 10.1016/j.isprsjprs.2020.07.001 · DOI
  20. 10.2352/ISSN.2470-1173.2016.10.ROBVIS-392 · DOI
  21. 10.1109/TGRS.2018.2858817 · DOI
  22. 10.3390/rs10010144 · DOI
  23. 10.3390/rs11242970 · DOI
  24. 10.1109/TGRS.2020.3014312 · DOI
  25. 10.1109/ACCESS.2019.2940527 · DOI
  26. 10.3390/rs12132161 · DOI
  27. 10.3390/rs12071195 · DOI
  28. 10.1109/ICCV.2017.244 · DOI · Paper page
  29. 10.1109/CVPR42600.2020.00414 · DOI
  30. 10.1109/ICCV.2019.00693 · DOI
  31. Hoffman, 2016, FCNs in the wild: Pixel-level adversarial and constraint-based adaptation
  32. 10.1109/ICCV.2017.220 · DOI
  33. Hoffman, Cycada: Cycle-consistent adversarial domain adaptation, 1989
  34. 10.1109/CVPR.2018.00712 · DOI
  35. 10.1109/CVPR.2018.00780 · DOI · Paper page
  36. 10.1109/CVPR.2019.00262 · DOI · Paper page
  37. 10.1109/ICCV.2019.00154 · DOI
  38. 10.1109/CVPR.2019.00261 · DOI
  39. Zheng, 2019, Unsupervised scene adaptation with memory regularization in vivo
  40. 10.1109/CVPR42600.2020.00382 · DOI
  41. Zou, 2018, Domain adaptation for semantic segmentation Via class-balanced self-training, 10.1007/978-3-030-01219-9_18 · DOI · Paper page
  42. 10.1007/s11263-020-01395-y · DOI
  43. 10.1109/ICCV.2019.00608 · DOI
  44. 10.3390/rs11111369 · DOI
  45. 10.1109/TGRS.2020.3035561 · DOI
  46. 10.1109/TGRS.2020.3020804 · DOI
  47. 10.1080/01431161.2020.1757782 · DOI
  48. Chen, 2020, Deep Siamese domain adaptation convolutional neural network for cross-domain change detection in multispectral images
  49. 10.5194/isprs-archives-XLIII-B3-2020-1635-2020 · DOI
  50. 10.1109/LGRS.2020.2982783 · DOI
  51. 10.3390/rs12223815 · DOI
  52. 10.1109/TGRS.2020.3001584 · DOI
  53. 10.1109/JSTARS.2020.3031741 · DOI
  54. 10.1109/TGRS.2020.3006161 · DOI
  55. 10.1109/CVPR.2019.00326 · DOI · Paper page
  56. Tarvainen, 2017, Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
  57. 10.1109/CVPR.2019.00320 · DOI
  58. Mnih, 2013, Machine Learning for Aerial Image Labeling

Cited by

Sorted by citations

Metadata

Authors
Peng, D., Guan, H., Zang, Y., & Bruzzone, L.
ORCID
Venue
IEEE Transactions on Geoscience and Remote Sensing
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2022
Volume
60
Pages
1-17
ISSN
  • 0196-2892
  • 1558-0644
DOI
10.1109/tgrs.2021.3093004
Cited by
33
References
1
Licence
Funders
  • National Natural Science Foundation of China (41801386, 41671454)
  • Natural Science Foundation of Jiangsu Province (BK20180797)
  • Startup Project for Introducing Talent of Nanjing University of Information Science and Technology (2018r029)
  • China Scholarship Council (201908320183)

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