CoChat
Sign Up
Cited by 675

The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.

Domain Adaptation for the Classification of Remote Sensing Data: An Overview of Recent Advances

Tuia, Devis, Persello, Claudio, Bruzzone, Lorenzo·2016·IEEE Geoscience and Remote Sensing Magazine
DOI 10.1109/mgrs.2016.2548504
Open this paper in CoChat — free account

Overview

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

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Integrity signals

Registry

Crossref · 10.1109/mgrs.2016.2548504

Cites

5 of 5 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.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

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?

  • Even if a practicable deep model is already trained on a well-annotated dataset, it may not be valid for other geographical areas or sensors because of feature distribution shifts between source and target domains.

    “Even if a practicable deep model is already trained on a well-annotated dataset, it may not be valid for other geographical areas or sensors because of the feature distribution shifts between the source and target domains (Tuia et al., 2016, Tong et al., 2020, Huang et al., 2023).”

    From Enabling country-scale land cover mapping with meter-resolution satellite imagery (2023) · cites this paper as Tuia et al., 2016

    The Introduction says a pre-trained model may not transfer accurately to a new image, and the Transfer Learning and Domain Adaptation section describes different geographical areas and shifts in feature distributions. The discussion of mosaicking also explains why a model trained for one sensor may not work with another. These passages concern classifiers generally, however; they do not establish the claim specifically for deep models. (LLM, conf=0.84)

    Experimental — accuracy not yet measured

  • To adapt DCNNs to a new domain, having examples of its feature distribution is the best way.

    “To adapt DCNNs to a new domain, there is no better way than having examples of its feature distribution (Tuia et al., 2016).”

    From Enabling country-scale land cover mapping with meter-resolution satellite imagery (2023) · cites this paper as Tuia et al., 2016

    The section “Adaptation of the classifier by active learning” says that labeled examples from the target domain can efficiently help adapt a classifier. It does not address DCNNs specifically or establish that having examples of the target feature distribution is the best way to adapt them. Page numbers are unavailable in our copy. (LLM, conf=0.85)

    Experimental — accuracy not yet measured

  • Diverse imaging conditions lead to shifts in feature distributions of ground objects, which causes the classification method optimal for the source domain to drop drastically in performance on the target domain.

    “The attendant problem is that diverse imaging conditions will lead to shifts in feature distributions of ground objects, which causes the classification method optimal for certain annotated images (referred to as the source domain) to drop drastically in performance on newly acquired images (referred to as the target domain) (Tuia et al., 2016, Tong et al., 2020).”

    From Enabling country-scale land cover mapping with meter-resolution satellite imagery (2023) · cites this paper as Tuia et al., 2016

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

Flagged first, then by citations

Research works printed but not linked: 74

  1. stumpf, 0, Active learning in the spatial-domain for landslide mapping in remote sensing images, Proc Euro Conf Machine Learn (ECML) Active Learning in Real-World Applications Workshop
  2. 10.1109/TGRS.2011.2168534 · DOI
  3. 10.1201/b11656-18 · DOI
  4. 10.1109/JPROC.2012.2231951 · DOI
  5. 10.1109/JSTARS.2014.2302333 · DOI
  6. 10.1109/TGRS.2013.2249522 · DOI
  7. 10.1109/LGRS.2015.2391297 · DOI
  8. 10.1371/journal.pone.0148655 · DOI
  9. 10.1109/LGRS.2013.2255258 · DOI
  10. 10.1109/TGRS.2014.2317499 · DOI
  11. 10.1109/TGRS.2014.2300189 · DOI
  12. luo, 2005, Active learning to recognize multiple types of plankton, J Mach Learn Res, 6, 589
  13. 10.1109/TGRS.2007.912445 · DOI
  14. 10.1109/TGRS.2004.842481 · DOI
  15. 10.1109/TGRS.2015.2503885 · DOI
  16. 10.1109/TGRS.2009.2019636 · DOI
  17. 10.1016/j.isprsjprs.2015.02.005 · DOI
  18. 10.1109/TIP.2006.888195 · DOI
  19. 10.1109/TGRS.2014.2377785 · DOI
  20. 10.1117/12.829645 · DOI
  21. sun, 2013, Learn multiple-kernel SVMs for domain adaptation in hyperspectral data, IEEE Geosci Remote Sens Lett, 10, 1224, 10.1109/LGRS.2012.2236818 · DOI
  22. 10.1109/LGRS.2008.916070 · DOI
  23. 10.1109/TGRS.2012.2200043 · DOI
  24. 10.1109/TGRS.2010.2076287 · DOI
  25. 10.1109/LGRS.2012.2220516 · DOI
  26. 10.1109/TGRS.2012.2192740 · DOI
  27. 10.1109/IGARSS.2008.4778790 · DOI
  28. 10.1109/TGRS.2007.910220 · DOI
  29. 10.1109/LGRS.2012.2227297 · DOI
  30. 10.1109/JSTARS.2012.2202881 · DOI
  31. settles, 2012, Active Learning, 10.1007/978-3-031-01560-1 · DOI
  32. 10.1109/JSTSP.2011.2139193 · DOI
  33. 10.1109/TGRS.2013.2295819 · DOI
  34. 10.1016/j.rse.2010.10.011 · DOI
  35. 10.1109/TGRS.2011.2174154 · DOI
  36. 10.1109/TGRS.2012.2198654 · DOI
  37. 10.1109/TGRS.2012.2195727 · DOI
  38. 10.1109/TGRS.2014.2305805 · DOI
  39. huang, 0, Correcting sample selection bias by unlabeled data, Proc 21st Annu Conf Neural Inform Proc Syst, 601
  40. 10.1109/TGRS.2012.2200045 · DOI
  41. 10.1109/LGRS.2015.2512999 · DOI
  42. 10.1109/TGRS.2007.894550 · DOI
  43. 10.1109/TGRS.2006.877950 · DOI
  44. 10.1109/TGRS.2006.878442 · DOI
  45. 10.1016/S1566-2535(02)00091-X · DOI
  46. 10.1109/TGRS.2002.803794 · DOI
  47. 10.1016/S0167-8655(02)00053-3 · DOI
  48. 10.1109/36.905255 · DOI
  49. 10.1109/IGARSS.2011.6049404 · DOI
  50. 10.1016/j.rse.2012.03.013 · DOI
  51. fleming, 1975, Computer-aided analysis of LANDSAT-I MSS data: A comparison of three approaches, including a ‘modified clustering’ approach, Lab Applicat Remote Sensing Inform Note 072475
  52. marcos gonzalez, 0, Weakly supervised alignment of multisensor images, Proc IEEE Int Geosci Remote Sens Symp (IGARSS), 2588
  53. 10.1016/j.rse.2004.12.015 · DOI
  54. 10.7551/mitpress/9780262170055.001.0001 · DOI · Paper page
  55. 10.1109/MSP.2014.2347059 · DOI
  56. 10.7551/mitpress/9780262017091.001.0001 · DOI
  57. 10.1016/j.isprsjprs.2015.05.004 · DOI
  58. 10.1016/j.rse.2011.04.022 · DOI
  59. 10.1109/JSTARS.2015.2420582 · DOI
  60. 10.1016/j.rse.2011.10.014 · DOI
  61. 10.1080/13658816.2013.865189 · DOI
  62. 10.1016/j.jag.2012.12.004 · DOI
  63. 10.1109/JSTARS.2012.2222356 · DOI
  64. 10.1109/JPROC.2015.2449668 · DOI
  65. 10.1109/TGRS.2013.2246837 · DOI
  66. 10.1016/j.isprsjprs.2014.03.016 · DOI
  67. zhang, 2014, Single-source domain adaptation with target and conditional shift, Regularization Optimization Kernels and Support Vector Machines
  68. 10.1109/JSTARS.2015.2500961 · DOI
  69. 10.1109/TGRS.2011.2105490 · DOI
  70. 10.1016/j.patcog.2010.09.013 · DOI
  71. 10.1109/TGRS.2015.2449736 · DOI
  72. 10.1109/WACV.2013.6475043 · DOI
  73. 10.1109/LGRS.2015.2491605 · DOI
  74. 10.1109/JSTARS.2015.2449738 · DOI

Cited by

Sorted by citations

Metadata

Authors
Tuia, D., Persello, C., & Bruzzone, L.
ORCID
Tuia, Devis
Venue
IEEE Geoscience and Remote Sensing Magazine
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2016-06
Volume
4
Issue
2
Pages
41-57
ISSN
2168-6831
DOI
10.1109/mgrs.2016.2548504
Cited by
675
References
5
Licence
ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html (vor)

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